{
  "$schema": "https://tokenscost.com/data/pricing.schema.json",
  "source": "https://tokenscost.com",
  "canonical": "https://tokenscost.com/data/pricing.json",
  "license": "CC-BY-4.0",
  "licenseUrl": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "Pricing data via Tokenscost (tokenscost.com)",
  "generatedAt": "2026-10-04T16:24:12.115Z",
  "lastUpdated": "2026-10-04",
  "unit": "USD per 1,000,000 tokens",
  "sources": {
    "openai": "https://platform.openai.com/docs/pricing",
    "anthropic": "https://www.anthropic.com/pricing",
    "google": "https://ai.google.dev/gemini-api/docs/pricing",
    "xai": "https://docs.x.ai/developers/pricing",
    "deepseek": "https://api-docs.deepseek.com/quick_start/pricing",
    "meta": "https://www.together.ai/pricing",
    "mistral": "https://mistral.ai/pricing",
    "perplexity": "https://docs.perplexity.ai/guides/pricing",
    "ibm": "https://www.ibm.com/products/watsonx-ai/pricing",
    "microsoft": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/microsoft/",
    "amazon": "https://aws.amazon.com/bedrock/pricing/",
    "moonshot": "https://platform.kimi.ai/docs/pricing/chat",
    "together": "https://www.together.ai/pricing",
    "fireworks": "https://fireworks.ai/pricing",
    "antling": "https://www.ant-ling.com/en/"
  },
  "modelCount": 446,
  "models": [
    {
      "id": "gpt-5.4-nano",
      "name": "GPT-5.4 Nano",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.4,
      "contextWindow": 128000,
      "notes": "Classification, routing, simple tasks",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-4.1-nano",
      "name": "GPT-4.1 Nano",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 1000000,
      "notes": "High-volume, low-latency workloads",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.4-mini",
      "name": "GPT-5.4 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.6,
      "contextWindow": 128000,
      "notes": "Production apps, moderate complexity",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-4.1-mini",
      "name": "GPT-4.1 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.6,
      "contextWindow": 1000000,
      "notes": "Structured tasks, cost-efficient coding",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "o4-mini",
      "name": "o4-mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 1.1,
      "outputPricePerM": 4.4,
      "contextWindow": 200000,
      "notes": "Math, logic, structured reasoning",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "o3-mini",
      "name": "o3-mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 1.1,
      "outputPricePerM": 4.4,
      "contextWindow": 200000,
      "notes": "Budget reasoning tasks",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.2",
      "name": "GPT-5.2",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 1.75,
      "outputPricePerM": 14,
      "contextWindow": 128000,
      "notes": "Coding, analysis",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "o3",
      "name": "o3",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 200000,
      "notes": "Complex multi-step reasoning",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-4.1",
      "name": "GPT-4.1",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 1000000,
      "notes": "Legacy — 1M context, still strong on coding/instructions",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-6-astra",
      "name": "GPT-6 Astra",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 10,
      "outputPricePerM": 50,
      "contextWindow": 1050000,
      "notes": "Released Sept 2026 — GPT-6 flagship. $10/$50 per 1M for prompts under 272K tokens; long-context requests (>272K input) bill at $20/$75. Cached input $1.00/M, cache writes $12.50/M",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.6",
      "name": "GPT-5.6",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 6,
      "outputPricePerM": 36,
      "contextWindow": 400000,
      "notes": "Released 2026 — next-gen flagship; deeper reasoning, expanded 400K context, improved multimodal and agentic performance",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.5",
      "name": "GPT-5.5",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 5,
      "outputPricePerM": 30,
      "contextWindow": 256000,
      "notes": "Released Apr 23, 2026 — most intuitive flagship; doubled per-token pricing vs GPT-5.4",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.5-pro",
      "name": "GPT-5.5 Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 30,
      "outputPricePerM": 180,
      "contextWindow": 256000,
      "notes": "Frontier reasoning tier — pricing unchanged from GPT-5.4 Pro",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.4",
      "name": "GPT-5.4",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2.5,
      "outputPricePerM": 15,
      "contextWindow": 128000,
      "notes": "General purpose, agents, coding",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "gpt-5.4-pro",
      "name": "GPT-5.4 Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 30,
      "outputPricePerM": 180,
      "contextWindow": 256000,
      "notes": "Complex reasoning, research",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken"
    },
    {
      "id": "claude-haiku-4.5",
      "name": "Claude Haiku 4.5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 1,
      "outputPricePerM": 5,
      "contextWindow": 200000,
      "notes": "Classification, chat, extraction",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-sonnet-4.5",
      "name": "Claude Sonnet 4.5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 200000,
      "notes": "Recommended default, strong coding",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-sonnet-4.6",
      "name": "Claude Sonnet 4.6",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 200000,
      "notes": "Production workhorse, instruction following",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-opus-4.6",
      "name": "Claude Opus 4.6",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 1000000,
      "notes": "Deep reasoning, long documents, coding",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-fable-5",
      "name": "Claude Fable 5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 10,
      "outputPricePerM": 50,
      "contextWindow": 1000000,
      "notes": "Mythos-class flagship (Jun 9, 2026) — state-of-the-art coding, vision, long-horizon agentic work",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-09"
    },
    {
      "id": "claude-opus-4.8",
      "name": "Claude Opus 4.8",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 1000000,
      "notes": "Previous Anthropic flagship — frontier reasoning, agentic coding, 1M context",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-05-28"
    },
    {
      "id": "claude-opus-4.7",
      "name": "Claude Opus 4.7",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 1000000,
      "notes": "Frontier reasoning, agentic coding, long-context analysis",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-opus-4.5",
      "name": "Claude Opus 4.5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 200000,
      "notes": "Previous-gen flagship, stable versioned",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-2.0-flash-lite",
      "name": "Gemini 2.0 Flash-Lite",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.075,
      "outputPricePerM": 0.3,
      "contextWindow": 1000000,
      "notes": "Ultra-affordable high-volume tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-2.5-flash-lite",
      "name": "Gemini 2.5 Flash-Lite",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 1000000,
      "notes": "Cheapest current Gemini — high-volume tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-2.0-flash",
      "name": "Gemini 2.0 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 1000000,
      "notes": "Previous-gen fast model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-3.1-flash-lite",
      "name": "Gemini 3.1 Flash-Lite",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.25,
      "outputPricePerM": 1.5,
      "contextWindow": 1000000,
      "notes": "Budget with newer capabilities",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-2.5-flash",
      "name": "Gemini 2.5 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.3,
      "outputPricePerM": 2.5,
      "contextWindow": 1000000,
      "notes": "High-throughput, cost-sensitive tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-3-flash",
      "name": "Gemini 3 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.5,
      "outputPricePerM": 3,
      "contextWindow": 1000000,
      "notes": "Fast reasoning, good value",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-2.5-pro",
      "name": "Gemini 2.5 Pro",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 1.25,
      "outputPricePerM": 10,
      "inputPricePerMHighContext": 2.5,
      "outputPricePerMHighContext": 15,
      "highContextThreshold": null,
      "contextWindow": 2000000,
      "notes": "Tiered pricing: ≤200K vs >200K input context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-3.1-pro",
      "name": "Gemini 3.1 Pro",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 2,
      "outputPricePerM": 12,
      "contextWindow": 1000000,
      "notes": "New flagship (Feb 2026) — top-tier reasoning + native video",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemini-3-pro",
      "name": "Gemini 3 Pro",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 2,
      "outputPricePerM": 12,
      "contextWindow": 2000000,
      "notes": "Frontier multimodal, agentic capabilities",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "claude-opus-5.5",
      "name": "Claude Opus 5.5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 4,
      "outputPricePerM": 20,
      "contextWindow": 1000000,
      "notes": "Frontier agentic coding and long-horizon reasoning",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "claude-sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1000000,
      "notes": "Balanced coding, agents and RAG at 1M context",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1050000,
      "notes": "Latest GPT-6 workhorse for coding and agents",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6.1-sol-pro",
      "name": "GPT-6.1 Sol Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1050000,
      "notes": "Extended-reasoning GPT-6.1 Sol variant",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6-sol",
      "name": "GPT-6 Sol",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1050000,
      "notes": "General-purpose GPT-6 model for coding and agents",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6-sol-pro",
      "name": "GPT-6 Sol Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1050000,
      "notes": "Extended-reasoning GPT-6 Sol variant",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6-luna",
      "name": "GPT-6 Luna",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.5,
      "contextWindow": 1050000,
      "notes": "Ultra-low-cost high-volume GPT-6 tier",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gpt-6-luna-pro",
      "name": "GPT-6 Luna Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.5,
      "contextWindow": 1050000,
      "notes": "Low-cost GPT-6 tier with extended reasoning",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "tiktoken",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "gemini-3.8-flash",
      "name": "Gemini 3.8 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.75,
      "outputPricePerM": 3.75,
      "contextWindow": 1048576,
      "notes": "Fast multimodal workhorse with 1M context",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "qwen3.8-max-prime",
      "name": "Qwen3.8 Max Prime",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 4,
      "outputPricePerM": 12,
      "contextWindow": 1000000,
      "notes": "Top-tier Qwen reasoning model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "qwen3.8-max",
      "name": "Qwen3.8 Max",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 1000000,
      "notes": "Qwen flagship for coding and multilingual tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "qwen3.8-omni-flash",
      "name": "Qwen3.8 Omni Flash",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.47,
      "contextWindow": 1000000,
      "notes": "Low-cost omni-modal model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "glm-5.3-prime",
      "name": "GLM-5.3 Prime",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 2.8,
      "outputPricePerM": 8.8,
      "contextWindow": 1000000,
      "notes": "Zhipu flagship for agentic coding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "glm-5.3-flashx",
      "name": "GLM-5.3 FlashX",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.37,
      "outputPricePerM": 1.25,
      "contextWindow": 1048576,
      "notes": "Fast, cheap GLM tier with 1M context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "mimo-v2.6-pro",
      "name": "MiMo V2.6 Pro",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.435,
      "outputPricePerM": 0.87,
      "contextWindow": 1050000,
      "notes": "Low-cost Xiaomi flagship with 1M context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "mimo-v2.6-flash",
      "name": "MiMo V2.6 Flash",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.14,
      "outputPricePerM": 0.28,
      "contextWindow": 1050000,
      "notes": "Very cheap high-throughput Xiaomi model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "mimo-v2.6-pro-ultraspeed",
      "name": "MiMo V2.6 Pro UltraSpeed",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 4.35,
      "outputPricePerM": 8.7,
      "contextWindow": 1048576,
      "notes": "Low-latency premium MiMo V2.6 Pro serving",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "muse-spark-1.3",
      "name": "Muse Spark 1.3",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 1.25,
      "outputPricePerM": 4.25,
      "contextWindow": 1048576,
      "notes": "Meta's latest hosted model with 1M context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "command-a-plus",
      "name": "Command A+",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.3,
      "outputPricePerM": 1.5,
      "contextWindow": 192000,
      "notes": "Enterprise RAG and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-10-04"
    },
    {
      "id": "grok-4.7",
      "name": "Grok 4.7",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "inputPricePerMHighContext": 4,
      "outputPricePerMHighContext": 12,
      "highContextThreshold": 200000,
      "contextWindow": 500000,
      "notes": "Latest xAI frontier model for coding, agentic tasks, and knowledge work. Text and image input; prompts ≥200K tokens use the $4/$12 long-context tier.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-09-23"
    },
    {
      "id": "grok-4.6",
      "name": "Grok 4.6",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 2000000,
      "notes": "Frontier agentic coding and long-running agents — matches GPT-5.6 on AA Intelligence Index",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-08-14"
    },
    {
      "id": "grok-4.6-fast",
      "name": "Grok 4.6 Fast",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 4,
      "outputPricePerM": 12,
      "contextWindow": 2000000,
      "notes": "Low-latency Grok 4.6 variant — 2x price of standard 4.6",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "lastUpdated": "2026-08-14"
    },
    {
      "id": "grok-4.1-fast",
      "name": "Grok 4.1 Fast",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.5,
      "contextWindow": 2000000,
      "notes": "Most workloads, long documents, agent workflows",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "grok-4.1",
      "name": "Grok 4.1",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 2000000,
      "notes": "Long-context flagship with native tool use and search",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-4.1-mini",
      "name": "Grok 4.1 Mini",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 1000000,
      "notes": "Smallest 4.1 variant — RAG and classification",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-4",
      "name": "Grok 4",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 256000,
      "notes": "Complex reasoning, coding with tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-4-heavy",
      "name": "Grok 4 Heavy",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 6,
      "outputPricePerM": 30,
      "contextWindow": 256000,
      "notes": "Multi-agent parallel reasoning — frontier ARC-AGI / HLE scores",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-4-mini",
      "name": "Grok 4 Mini",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 256000,
      "notes": "Distilled Grok 4 for high-throughput chat and tools",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-3",
      "name": "Grok 3",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 131072,
      "notes": "Previous-gen flagship — strong general reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-3-mini",
      "name": "Grok 3 Mini",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.5,
      "contextWindow": 131072,
      "notes": "Budget Grok 3 for chat and lightweight agents",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-3-reasoning",
      "name": "Grok 3 Reasoning",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 131072,
      "notes": "Extended chain-of-thought reasoning variant",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-2-vision",
      "name": "Grok 2 Vision",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 32768,
      "notes": "Multimodal Grok 2 — charts, documents, screenshots",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-code-fast-1",
      "name": "Grok Code Fast 1",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.2,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "Coding-specialized Grok for IDEs and agentic dev",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "grok-voice",
      "name": "Grok Voice",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 1,
      "outputPricePerM": 4,
      "contextWindow": 32000,
      "notes": "Realtime voice-mode model for spoken interactions",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "deepseek-v3.2",
      "name": "DeepSeek V3.2",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.28,
      "outputPricePerM": 0.42,
      "contextWindow": 128000,
      "notes": "Best value overall, 90% cache discount",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "deepseek-v4-1",
      "name": "DeepSeek V4.1",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.42,
      "outputPricePerM": 1.68,
      "contextWindow": 512000,
      "notes": "Refreshed V4 flagship — sharper agentic coding, 512K context, 90% cache-hit discount",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-09-15"
    },
    {
      "id": "deepseek-v4-pro",
      "name": "DeepSeek V4 Pro",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.55,
      "outputPricePerM": 2.2,
      "contextWindow": 256000,
      "notes": "1.6T-param MoE flagship (49B active), frontier reasoning at open-weight prices",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-04-25"
    },
    {
      "id": "deepseek-v4-flash",
      "name": "DeepSeek V4 Flash",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.14,
      "outputPricePerM": 0.55,
      "contextWindow": 128000,
      "notes": "284B-param MoE (13B active), high-throughput chat/RAG/extraction",
      "batchDiscount": 0.5,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-04-25"
    },
    {
      "id": "deepseek-r1",
      "name": "DeepSeek R1",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.55,
      "outputPricePerM": 2.19,
      "contextWindow": 128000,
      "notes": "Reasoning at budget prices",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-3.1-8b",
      "name": "Llama 3.1 8B Instruct",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.05,
      "contextWindow": 128000,
      "notes": "Fast, cost-efficient local-style inference. Pricing via Together AI.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-3.3-70b",
      "name": "Llama 3.3 70B Instruct",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.12,
      "outputPricePerM": 0.12,
      "contextWindow": 128000,
      "notes": "Strong open-weight reasoning, coding, and tool use. Pricing via Together AI.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-3.2-90b-vision",
      "name": "Llama 3.2 90B Vision",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.25,
      "outputPricePerM": 0.25,
      "contextWindow": 128000,
      "notes": "Multimodal vision-language model for image understanding and text generation.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-3.1-405b",
      "name": "Llama 3.1 405B Instruct",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.5,
      "outputPricePerM": 0.5,
      "contextWindow": 128000,
      "notes": "Dense open-weight flagship, competitive with GPT-4-class models. Pricing via Together AI.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-4-scout",
      "name": "Llama 4 Scout",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.25,
      "contextWindow": 10000000,
      "notes": "10M context window — long-doc specialist. Pricing via Together AI.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-4-maverick",
      "name": "Llama 4 Maverick",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 1000000,
      "notes": "Meta's flagship MoE — 400B params, 17B active. Pricing via Together AI.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "llama-4-instruct",
      "name": "Llama 4 Instruct",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 1000000,
      "notes": "Dense Llama 4 variant, strong general-purpose reasoning and coding.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mistral-small",
      "name": "Mistral Small 3.1",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "High-throughput budget tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mistral-medium-3",
      "name": "Mistral Medium 3",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.4,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "Strong mid-tier Mistral with function calling",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mistral-large",
      "name": "Mistral Large 3",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "European provider, multilingual",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "magistral-medium-2",
      "name": "Magistral Medium 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 2,
      "outputPricePerM": 5,
      "contextWindow": 128000,
      "notes": "Frontier European reasoning model with extended chain-of-thought",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "magistral-small",
      "name": "Magistral Small",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Open-weight 24B reasoning model — math, science, code",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "codestral-25-10",
      "name": "Codestral 25.10",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 256000,
      "notes": "Code generation, completion, and FIM across 80+ languages",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "devstral-medium",
      "name": "Devstral Medium",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.4,
      "outputPricePerM": 2,
      "contextWindow": 256000,
      "notes": "Agentic coding — long-context repo edits and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "devstral-small",
      "name": "Devstral Small",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "Open-weight agentic coder for IDEs and local dev",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "ministral-8b",
      "name": "Ministral 8B",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.1,
      "contextWindow": 128000,
      "notes": "Edge-class 8B model — low-latency on-device chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "ministral-3b",
      "name": "Ministral 3B",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.04,
      "outputPricePerM": 0.04,
      "contextWindow": 128000,
      "notes": "Ultra-cheap 3B model for classification and routing",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "pixtral-large",
      "name": "Pixtral Large",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Multimodal flagship — vision, charts, document understanding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "pixtral-12b",
      "name": "Pixtral 12B",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.15,
      "contextWindow": 128000,
      "notes": "Open-weight 12B vision-language model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mistral-ocr",
      "name": "Mistral OCR",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 1,
      "outputPricePerM": 1,
      "contextWindow": 0,
      "notes": "Document OCR with layout and table extraction",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mistral-embed-2",
      "name": "Mistral Embed 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.1,
      "contextWindow": 32000,
      "notes": "Multilingual embeddings for RAG and clustering",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mistral-saba",
      "name": "Mistral Saba",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 32000,
      "notes": "Arabic + South-Asian language specialist",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mistral-nemo",
      "name": "Mistral NeMo",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.15,
      "contextWindow": 128000,
      "notes": "Open-weight 12B model co-developed with NVIDIA",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mixtral-8x22b",
      "name": "Mixtral 8x22B",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 64000,
      "notes": "Sparse mixture-of-experts open-weight model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "sonar",
      "name": "Sonar",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 1,
      "outputPricePerM": 1,
      "contextWindow": 127000,
      "notes": "Grounded web search at low cost",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "sonar-reasoning",
      "name": "Sonar Reasoning",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 1,
      "outputPricePerM": 5,
      "contextWindow": 127000,
      "notes": "Reasoning over live web results",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "sonar-deep-research",
      "name": "Sonar Deep Research",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 127000,
      "notes": "Multi-step deep research with sources",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "sonar-reasoning-pro",
      "name": "Sonar Reasoning Pro",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 127000,
      "notes": "Stronger reasoning + grounded search",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "sonar-pro",
      "name": "Sonar Pro",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 200000,
      "notes": "Advanced grounded search with citations",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "granite-3.3-2b-instruct",
      "name": "Granite 3.3 2B Instruct",
      "provider": "IBM",
      "providerLogo": "ibm",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.1,
      "contextWindow": 128000,
      "notes": "Ultra-cheap on-device/edge inference, classification, summarization on watsonx.ai",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "granite-3.3-8b-instruct",
      "name": "Granite 3.3 8B Instruct",
      "provider": "IBM",
      "providerLogo": "ibm",
      "inputPricePerM": 0.5,
      "outputPricePerM": 0.5,
      "contextWindow": 128000,
      "notes": "Enterprise RAG, summarization, function calling on watsonx.ai",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "phi-4",
      "name": "Phi-4",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 0.065,
      "outputPricePerM": 0.14,
      "contextWindow": 16000,
      "notes": "Low-latency coding, reasoning, and chat on Azure AI Foundry",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "nova-pro",
      "name": "Nova Pro",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 0.8,
      "outputPricePerM": 3.2,
      "contextWindow": 300000,
      "notes": "High-quality text, vision, and tool use via Amazon Bedrock",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "gemma-3-27b",
      "name": "Gemma 3 27B",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.08,
      "outputPricePerM": 0.16,
      "contextWindow": 128000,
      "notes": "Open-weight multimodal model for text and vision tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-8k",
      "name": "Moonshot V1 8K",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.2,
      "outputPricePerM": 2,
      "contextWindow": 8192,
      "notes": "Entry-level generation model for short-context tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-8k-vision-preview",
      "name": "Moonshot V1 8K Vision Preview",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.2,
      "outputPricePerM": 2,
      "contextWindow": 8192,
      "notes": "Vision-enabled preview for image + text tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-32k",
      "name": "Moonshot V1 32K",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 32768,
      "notes": "Mid-tier generation model with expanded context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-32k-vision-preview",
      "name": "Moonshot V1 32K Vision Preview",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 32768,
      "notes": "Vision-enabled preview with 32K context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-128k",
      "name": "Moonshot V1 128K",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 2,
      "outputPricePerM": 5,
      "contextWindow": 131072,
      "notes": "Max-context V1 generation model for long documents",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "moonshot-v1-128k-vision-preview",
      "name": "Moonshot V1 128K Vision Preview",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 2,
      "outputPricePerM": 5,
      "contextWindow": 131072,
      "notes": "Vision-enabled preview with 128K context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "kimi-k2-5",
      "name": "Kimi K2.5",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.6,
      "outputPricePerM": 3,
      "contextWindow": 262144,
      "notes": "Trillion-parameter multimodal flagship with 256K context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "kimi-k2-6",
      "name": "Kimi K2.6",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.95,
      "outputPricePerM": 4,
      "contextWindow": 262144,
      "notes": "Frontier-scale coding, long-context agentic workflows",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-k2-thinking",
      "name": "Kimi K2 Thinking",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 1.2,
      "outputPricePerM": 5,
      "contextWindow": 262144,
      "notes": "Reasoning-tuned K2 variant — extended chain-of-thought for math, code, science",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-k2-instruct",
      "name": "Kimi K2 Instruct",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.55,
      "outputPricePerM": 2.2,
      "contextWindow": 262144,
      "notes": "Open-weight 1T MoE instruct model — tool use, coding, agents",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-k2-mini",
      "name": "Kimi K2 Mini",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Distilled K2 for low-latency, high-throughput chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-k1-5",
      "name": "Kimi K1.5",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.4,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "Long-context multimodal reasoning model with RL post-training",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-k1-5-long",
      "name": "Kimi K1.5 Long",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.8,
      "outputPricePerM": 3.2,
      "contextWindow": 2000000,
      "notes": "2M-token context for full codebases and document corpora",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-latest",
      "name": "Kimi Latest",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2.5,
      "contextWindow": 200000,
      "notes": "Always-updated production endpoint tracking the newest Kimi release",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-vision",
      "name": "Kimi Vision",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.9,
      "outputPricePerM": 3.6,
      "contextWindow": 128000,
      "notes": "Multimodal vision-language model for charts, OCR, and UI understanding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-coder",
      "name": "Kimi Coder",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.65,
      "outputPricePerM": 2.6,
      "contextWindow": 262144,
      "notes": "Repo-scale code generation, refactoring, and agentic development",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-math",
      "name": "Kimi Math",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.8,
      "contextWindow": 128000,
      "notes": "Specialized math and theorem-proving variant",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-audio",
      "name": "Kimi Audio",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 0.8,
      "outputPricePerM": 3.2,
      "contextWindow": 64000,
      "notes": "Speech-in / speech-out multimodal audio model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "kimi-researcher",
      "name": "Kimi Researcher",
      "provider": "Moonshot",
      "providerLogo": "moonshot",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 262144,
      "notes": "Autonomous deep-research agent with browsing and citations",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-text-lite",
      "name": "MiniMax Text-Lite",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.08,
      "outputPricePerM": 0.24,
      "contextWindow": 128000,
      "notes": "Ultra-affordable entry model for chat and high-volume apps",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "minimax-vl-01",
      "name": "MiniMax VL-01",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.45,
      "outputPricePerM": 1.35,
      "contextWindow": 128000,
      "notes": "Vision-language MoE for multimodal reasoning and image understanding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "minimax-text-01",
      "name": "MiniMax Text-01",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.35,
      "outputPricePerM": 1.05,
      "contextWindow": 256000,
      "notes": "Flagship text model with strong reasoning and long-context RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "minimax-pro",
      "name": "MiniMax Pro",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.9,
      "outputPricePerM": 2.7,
      "contextWindow": 256000,
      "notes": "Maximum capability with extended context reasoning and agentic tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "minimax-m3",
      "name": "MiniMax M3",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2.2,
      "contextWindow": 4000000,
      "notes": "Flagship MoE with 4M-token context — agentic reasoning, coding, and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-m2",
      "name": "MiniMax M2",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.3,
      "outputPricePerM": 1.2,
      "contextWindow": 1000000,
      "notes": "230B MoE optimized for agentic coding and end-to-end tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-m1",
      "name": "MiniMax M1",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.4,
      "outputPricePerM": 2.2,
      "contextWindow": 1000000,
      "notes": "456B open-weight MoE reasoning model with 1M-token context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-abab-6-5-chat",
      "name": "abab6.5-chat",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.3,
      "contextWindow": 245000,
      "notes": "Trillion-parameter MoE chat model with 245K context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-abab-6-5s-chat",
      "name": "abab6.5s-chat",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.14,
      "outputPricePerM": 0.14,
      "contextWindow": 245000,
      "notes": "Lighter, faster abab6.5 sibling for high-volume chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-abab-6-5t-chat",
      "name": "abab6.5t-chat",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.07,
      "outputPricePerM": 0.07,
      "contextWindow": 8192,
      "notes": "Tiny abab6.5 variant for ultra-low-latency apps",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-abab-5-5-chat",
      "name": "abab5.5-chat",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 2.13,
      "outputPricePerM": 2.13,
      "contextWindow": 16384,
      "notes": "Earlier-generation abab dense model — kept for compatibility",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "minimax-speech-2-5-hd",
      "name": "MiniMax Speech-2.5 HD",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 60,
      "outputPricePerM": 0,
      "contextWindow": 5000,
      "notes": "Multilingual expressive TTS (~$0.06/1K chars) — 30+ languages, voice cloning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-lite",
      "name": "MiMo Lite",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.06,
      "outputPricePerM": 0.18,
      "contextWindow": 128000,
      "notes": "Ultra-affordable entry model for chat and high-volume apps",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mimo-text",
      "name": "MiMo Text",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.25,
      "outputPricePerM": 0.75,
      "contextWindow": 256000,
      "notes": "Strong mid-tier with reasoning, coding, and long-context RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mimo-pro",
      "name": "MiMo Pro",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 256000,
      "notes": "Flagship model with extended context and agentic tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mimo-vision",
      "name": "MiMo Vision",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Vision-language model for multimodal reasoning and image understanding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "mimo-v2-5-pro",
      "name": "MiMo V2.5 Pro",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 256000,
      "notes": "Flagship MiMo with extended context and agentic tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-v2-5",
      "name": "MiMo V2.5",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.45,
      "outputPricePerM": 1.35,
      "contextWindow": 256000,
      "notes": "Open-weight MoE flagship — strong reasoning, coding, and RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-v2-5-lite",
      "name": "MiMo V2.5 Lite",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "Fast, low-cost MiMo variant for chat, classification, and routing",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-reasoner",
      "name": "MiMo Reasoner",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.55,
      "outputPricePerM": 2.2,
      "contextWindow": 128000,
      "notes": "Reasoning-tuned MoE for math, science, and multi-step problems",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-coder",
      "name": "MiMo Coder",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Code-specialized MiMo for repo-scale coding and refactoring",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "mimo-audio",
      "name": "MiMo Audio",
      "provider": "Xiaomi",
      "providerLogo": "mimo",
      "inputPricePerM": 0.35,
      "outputPricePerM": 1.05,
      "contextWindow": 32000,
      "notes": "End-to-end speech + text model for voice agents and audio reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hy3-lite",
      "name": "Hy3 Lite",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.06,
      "outputPricePerM": 0.18,
      "contextWindow": 128000,
      "notes": "Ultra-fast MoE for chat, classification, and high-volume apps",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "hy3-preview",
      "name": "Hy3 Preview",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.35,
      "outputPricePerM": 1.05,
      "contextWindow": 128000,
      "notes": "Frontier preview with strong reasoning, coding, and agentic workflows",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "hy3-pro",
      "name": "Hy3 Pro",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.9,
      "outputPricePerM": 2.7,
      "contextWindow": 256000,
      "notes": "Production-grade MoE flagship for complex agents and long-context RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "hy3-max",
      "name": "Hy3 Max",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Maximum capability with extended context reasoning and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx"
    },
    {
      "id": "hunyuan-t1",
      "name": "Hunyuan-T1",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.14,
      "outputPricePerM": 0.55,
      "contextWindow": 128000,
      "notes": "Hybrid Mamba-Transformer reasoning model — strong math and coding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-turbo",
      "name": "Hunyuan-Turbo",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "Production MoE flagship — fast, multilingual, function calling",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-turbos",
      "name": "Hunyuan-TurboS",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.11,
      "outputPricePerM": 0.42,
      "contextWindow": 256000,
      "notes": "Hybrid Transformer-Mamba balance of speed and quality",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-large",
      "name": "Hunyuan-Large",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "389B open-weight MoE — 52B active params, strong general reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-standard",
      "name": "Hunyuan-Standard",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.06,
      "outputPricePerM": 0.13,
      "contextWindow": 32000,
      "notes": "Default Tencent Cloud model for everyday chat and RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-standard-256k",
      "name": "Hunyuan-Standard-256K",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.21,
      "outputPricePerM": 0.84,
      "contextWindow": 256000,
      "notes": "Long-context variant of Hunyuan Standard for document QA",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-vision",
      "name": "Hunyuan-Vision",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 32000,
      "notes": "Multimodal vision-language model for image + text reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-code",
      "name": "Hunyuan-Code",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 128000,
      "notes": "Code-specialized Hunyuan for repo-scale coding and refactoring",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-role",
      "name": "Hunyuan-Role",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 32000,
      "notes": "Role-play tuned variant for character agents and companions",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-functioncall",
      "name": "Hunyuan-FunctionCall",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 32000,
      "notes": "Tool-use tuned variant optimized for function calling pipelines",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "hunyuan-embedding",
      "name": "Hunyuan-Embedding",
      "provider": "Tencent",
      "providerLogo": "hy3",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0,
      "contextWindow": 1024,
      "notes": "Tencent embedding model for semantic search and RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "command-a-03-2025",
      "name": "Command A",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 256000,
      "notes": "Cohere's flagship enterprise model for agentic RAG and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "command-r-plus-08-2024",
      "name": "Command R+",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 128000,
      "notes": "Multilingual reasoning and long-context RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "command-r-08-2024",
      "name": "Command R",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Cost-efficient RAG and tool calling at scale",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "command-r7b-12-2024",
      "name": "Command R7B",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.0375,
      "outputPricePerM": 0.15,
      "contextWindow": 128000,
      "notes": "Compact 7B model for low-latency edge deployments",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "qwen3-max",
      "name": "Qwen3 Max",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 1.6,
      "outputPricePerM": 6.4,
      "contextWindow": 256000,
      "notes": "Alibaba's flagship multilingual reasoning and coding model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "qwen3-plus",
      "name": "Qwen3 Plus",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 131072,
      "notes": "Balanced general-purpose model for production workloads",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "qwen3-coder",
      "name": "Qwen3 Coder",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 1,
      "outputPricePerM": 5,
      "contextWindow": 1000000,
      "notes": "Agentic coding specialist with 1M-token context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "qwen3-turbo",
      "name": "Qwen3 Turbo",
      "provider": "Qwen",
      "providerLogo": "qwen",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.2,
      "contextWindow": 131072,
      "notes": "High-throughput cost-efficient inference",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "glm-4.6",
      "name": "GLM-4.6",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.6,
      "outputPricePerM": 2.2,
      "contextWindow": 200000,
      "notes": "Zhipu's flagship reasoning and coding model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "glm-4.5-air",
      "name": "GLM-4.5 Air",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.2,
      "outputPricePerM": 1.1,
      "contextWindow": 128000,
      "notes": "Lightweight MoE for cost-sensitive agentic workloads",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "glm-4.5-flash",
      "name": "GLM-4.5 Flash",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.2,
      "contextWindow": 128000,
      "notes": "High-volume classification and retrieval",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "yi-lightning",
      "name": "Yi-Lightning",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 0.14,
      "outputPricePerM": 0.14,
      "contextWindow": 16384,
      "notes": "Low-latency flagship from 01.AI for chat and reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "yi-large",
      "name": "Yi-Large",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 3,
      "outputPricePerM": 3,
      "contextWindow": 32768,
      "notes": "Bilingual EN/ZH reasoning model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "yi-medium",
      "name": "Yi-Medium",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 0.5,
      "outputPricePerM": 0.5,
      "contextWindow": 16384,
      "notes": "Balanced cost-quality model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "reka-core",
      "name": "Reka Core",
      "provider": "Reka",
      "providerLogo": "reka",
      "inputPricePerM": 2,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "Multimodal flagship across text, image, audio, and video",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "reka-flash",
      "name": "Reka Flash",
      "provider": "Reka",
      "providerLogo": "reka",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "Fast multimodal model for production agents",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "reka-edge",
      "name": "Reka Edge",
      "provider": "Reka",
      "providerLogo": "reka",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1,
      "contextWindow": 64000,
      "notes": "On-device / edge-deployable multimodal model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "jamba-1.7-large",
      "name": "Jamba 1.7 Large",
      "provider": "AI21",
      "providerLogo": "ai21",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 256000,
      "notes": "Hybrid Mamba-Transformer flagship with 256K context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "jamba-1.7-mini",
      "name": "Jamba 1.7 Mini",
      "provider": "AI21",
      "providerLogo": "ai21",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.4,
      "contextWindow": 256000,
      "notes": "Cost-efficient hybrid SSM for long-context RAG",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "jamba-instruct",
      "name": "Jamba Instruct",
      "provider": "AI21",
      "providerLogo": "ai21",
      "inputPricePerM": 0.5,
      "outputPricePerM": 0.7,
      "contextWindow": 256000,
      "notes": "Instruction-tuned variant for enterprise deployments",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-10"
    },
    {
      "id": "together-llama-4-scout",
      "name": "Llama 4 Scout (Together AI)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 1000000,
      "notes": "Hosted open-weight inference — fast, affordable general purpose",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "together-llama-4-maverick",
      "name": "Llama 4 Maverick (Together AI)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 1000000,
      "notes": "Hosted open-weight inference — strong reasoning and coding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "together-qwen3-32b",
      "name": "Qwen3 32B (Together AI)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.8,
      "contextWindow": 128000,
      "notes": "Hosted Qwen3 32B for production agents and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "together-mixtral-8x22b",
      "name": "Mixtral 8x22B (Together AI)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 64000,
      "notes": "Hosted sparse MoE — multilingual and long-context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "together-deepseek-v3",
      "name": "DeepSeek V3 (Together AI)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.9,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "Hosted DeepSeek V3 with fast autoscaling inference",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "fireworks-llama-4-scout",
      "name": "Llama 4 Scout (Fireworks AI)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.09,
      "outputPricePerM": 0.25,
      "contextWindow": 1000000,
      "notes": "Fireworks-hosted Llama 4 Scout — ultra-fast inference",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "fireworks-llama-4-maverick",
      "name": "Llama 4 Maverick (Fireworks AI)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.18,
      "outputPricePerM": 0.5,
      "contextWindow": 1000000,
      "notes": "Fireworks-hosted Llama 4 Maverick — low-latency reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "fireworks-qwen3-32b",
      "name": "Qwen3 32B (Fireworks AI)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.25,
      "outputPricePerM": 0.7,
      "contextWindow": 128000,
      "notes": "Fireworks-hosted Qwen3 32B optimized for throughput",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "fireworks-mixtral-8x22b",
      "name": "Mixtral 8x22B (Fireworks AI)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 1.8,
      "outputPricePerM": 5.4,
      "contextWindow": 64000,
      "notes": "Fireworks-hosted Mixtral 8x22B with speculative decoding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "fireworks-mistral-small-3.1",
      "name": "Mistral Small 3.1 (Fireworks AI)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.13,
      "outputPricePerM": 0.5,
      "contextWindow": 128000,
      "notes": "Fireworks-hosted Mistral Small 3.1 for high-volume agents",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-11"
    },
    {
      "id": "gpt-5.6-mini",
      "name": "GPT-5.6 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.6,
      "contextWindow": 400000,
      "notes": "Compact GPT-5.6 for high-volume tasks",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-5.6-nano",
      "name": "GPT-5.6 Nano",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.08,
      "outputPricePerM": 0.32,
      "contextWindow": 400000,
      "notes": "Ultra-cheap GPT-5.6 variant",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "o5",
      "name": "OpenAI o5",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 6,
      "outputPricePerM": 24,
      "contextWindow": 300000,
      "notes": "o-series successor reasoning model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "o5-mini",
      "name": "OpenAI o5-mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 1.2,
      "outputPricePerM": 4.8,
      "contextWindow": 300000,
      "notes": "Cost-efficient o5 reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "o5-pro",
      "name": "OpenAI o5 Pro",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 15,
      "outputPricePerM": 60,
      "contextWindow": 300000,
      "notes": "Premium o5 reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 5,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-4.6",
      "name": "GPT-4.6",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 256000,
      "notes": "GPT-4.6 refresh",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-4.6-mini",
      "name": "GPT-4.6 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.3,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "GPT-4.6 mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-oss-200b",
      "name": "GPT-OSS 200B",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.6,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "OpenAI open-weight 200B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-oss-20b",
      "name": "GPT-OSS 20B",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 128000,
      "notes": "OpenAI open-weight 20B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-4.5-opus",
      "name": "Claude 4.5 Opus",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 18,
      "outputPricePerM": 90,
      "contextWindow": 500000,
      "notes": "Anthropic flagship",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-4.5-sonnet",
      "name": "Claude 4.5 Sonnet",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 3.5,
      "outputPricePerM": 17.5,
      "contextWindow": 500000,
      "notes": "Anthropic mid-tier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-4.5-haiku",
      "name": "Claude 4.5 Haiku",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 0.9,
      "outputPricePerM": 4.5,
      "contextWindow": 400000,
      "notes": "Fast Anthropic model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-opus",
      "name": "Claude 5 Opus",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 20,
      "outputPricePerM": 100,
      "contextWindow": 1000000,
      "notes": "Claude 5 frontier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-sonnet",
      "name": "Claude 5 Sonnet",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 4,
      "outputPricePerM": 20,
      "contextWindow": 1000000,
      "notes": "Claude 5 balanced",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-haiku",
      "name": "Claude 5 Haiku",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 1,
      "outputPricePerM": 5,
      "contextWindow": 500000,
      "notes": "Claude 5 fast tier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-thinking",
      "name": "Claude 5 Thinking",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 6,
      "outputPricePerM": 30,
      "contextWindow": 500000,
      "notes": "Claude 5 extended thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-3.5-flash",
      "name": "Gemini 3.5 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.6,
      "contextWindow": 2000000,
      "notes": "Next-gen Gemini Flash",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-3.5-flash-lite",
      "name": "Gemini 3.5 Flash Lite",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 1000000,
      "notes": "Cheap Gemini Flash Lite",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-3.5-pro",
      "name": "Gemini 3.5 Pro",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 2000000,
      "notes": "Next-gen Gemini Pro",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-4-pro",
      "name": "Gemini 4 Pro",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 5,
      "outputPricePerM": 25,
      "contextWindow": 2000000,
      "notes": "Gemini 4 frontier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-4-flash",
      "name": "Gemini 4 Flash",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 1000000,
      "notes": "Gemini 4 fast tier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-4-ultra",
      "name": "Gemini 4 Ultra",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 10,
      "outputPricePerM": 40,
      "contextWindow": 4000000,
      "notes": "Gemini 4 ultra reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemma-3-9b",
      "name": "Gemma 3 9B",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.15,
      "contextWindow": 128000,
      "notes": "Open Gemma 3 9B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-5-405b",
      "name": "Llama 5 405B",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 2.5,
      "outputPricePerM": 7.5,
      "contextWindow": 256000,
      "notes": "Meta flagship Llama 5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-5-70b",
      "name": "Llama 5 70B",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 256000,
      "notes": "Meta Llama 5 mid",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-5-8b",
      "name": "Llama 5 8B",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 256000,
      "notes": "Meta Llama 5 small",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-4-behemoth",
      "name": "Llama 4 Behemoth",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 4,
      "outputPricePerM": 12,
      "contextWindow": 512000,
      "notes": "Llama 4 Behemoth",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-4.1-scout",
      "name": "Llama 4.1 Scout",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 10000000,
      "notes": "Llama 4.1 Scout long-context",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-4.1-maverick",
      "name": "Llama 4.1 Maverick",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 1000000,
      "notes": "Llama 4.1 Maverick",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-guard-4",
      "name": "Llama Guard 4",
      "provider": "Meta",
      "providerLogo": "meta",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Safety-tuned Llama",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-small-4",
      "name": "Mistral Small 4",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 256000,
      "notes": "Mistral Small 4",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "codestral-3",
      "name": "Codestral 3",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 256000,
      "notes": "Code-tuned Mistral",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-nemo-2",
      "name": "Mistral NeMo 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.45,
      "contextWindow": 128000,
      "notes": "NeMo 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "pixtral-large-2",
      "name": "Pixtral Large 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Multimodal Pixtral",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "grok-5",
      "name": "Grok 5",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 4,
      "outputPricePerM": 16,
      "contextWindow": 1000000,
      "notes": "xAI Grok 5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "grok-5-mini",
      "name": "Grok 5 Mini",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 1000000,
      "notes": "Grok 5 mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "grok-5-fast",
      "name": "Grok 5 Fast",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 0.3,
      "outputPricePerM": 1,
      "contextWindow": 500000,
      "notes": "Grok 5 fast",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "grok-4-vision",
      "name": "Grok 4 Vision",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 3,
      "outputPricePerM": 12,
      "contextWindow": 500000,
      "notes": "Grok 4 Vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "grok-code-2",
      "name": "Grok Code 2",
      "provider": "xAI",
      "providerLogo": "xai",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 500000,
      "notes": "Grok code-tuned",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepseek-v4",
      "name": "DeepSeek V4",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "DeepSeek V4 general",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepseek-r2",
      "name": "DeepSeek R2",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.8,
      "contextWindow": 128000,
      "notes": "DeepSeek R2 reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepseek-r2-lite",
      "name": "DeepSeek R2 Lite",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.8,
      "contextWindow": 128000,
      "notes": "DeepSeek R2 lite",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepseek-coder-v3",
      "name": "DeepSeek Coder V3",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "DeepSeek code model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepseek-vl-2",
      "name": "DeepSeek VL 2",
      "provider": "DeepSeek",
      "providerLogo": "deepseek",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "DeepSeek vision-language",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "qwen3-235b-thinking",
      "name": "Qwen3 235B Thinking",
      "provider": "Alibaba",
      "providerLogo": "qwen",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Qwen3 thinking mode",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3.5,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "qwen3-coder-480b",
      "name": "Qwen3 Coder 480B",
      "provider": "Alibaba",
      "providerLogo": "qwen",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Qwen3 Coder flagship",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "qwen3-vl-72b",
      "name": "Qwen3 VL 72B",
      "provider": "Alibaba",
      "providerLogo": "qwen",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "Qwen3 VL multimodal",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "qwen3-omni-32b",
      "name": "Qwen3 Omni 32B",
      "provider": "Alibaba",
      "providerLogo": "qwen",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Qwen3 omni-modal",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5.2",
      "name": "GLM-5.2",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 1.4,
      "outputPricePerM": 4.2,
      "contextWindow": 1000000,
      "notes": "Z.ai GLM-5.2 — 744B params, 1M context, MIT license; #1 open on Agent Arena and Design Arena",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-17"
    },
    {
      "id": "glm-5",
      "name": "GLM-5",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 256000,
      "notes": "Zhipu GLM-5 flagship",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5-air",
      "name": "GLM-5 Air",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 256000,
      "notes": "GLM-5 Air",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5-flash",
      "name": "GLM-5 Flash",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.15,
      "contextWindow": 256000,
      "notes": "GLM-5 Flash free-tier-like",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5v",
      "name": "GLM-5V",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "GLM-5 vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "kimi-k3",
      "name": "Kimi K3",
      "provider": "Moonshot",
      "providerLogo": "kimi",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 1000000,
      "notes": "Moonshot Kimi K3 — $3.00/M input (cache miss), $0.30/M input (cache hit), $15.00/M output. Flat pricing across the full 1M-token context. Available via Moonshot AI and aggregators like OpenRouter.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-08-07"
    },
    {
      "id": "kimi-vl-a3b",
      "name": "Kimi VL A3B",
      "provider": "Moonshot",
      "providerLogo": "kimi",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "Kimi vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "command-r-plus-2",
      "name": "Command R+ 2",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 256000,
      "notes": "Cohere Command R+ refresh",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "command-r-2",
      "name": "Command R 2",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.3,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Cohere Command R refresh",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "aya-expanse-32b",
      "name": "Aya Expanse 32B",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Cohere multilingual Aya",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sonar-pro-2",
      "name": "Sonar Pro 2",
      "provider": "Perplexity",
      "providerLogo": "perplexity",
      "inputPricePerM": 4,
      "outputPricePerM": 16,
      "contextWindow": 200000,
      "notes": "Perplexity Sonar Pro 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nova-premier-2",
      "name": "Nova Premier 2",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 4,
      "outputPricePerM": 16,
      "contextWindow": 1000000,
      "notes": "Amazon Nova Premier 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nova-pro-2",
      "name": "Nova Pro 2",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 1,
      "outputPricePerM": 4,
      "contextWindow": 300000,
      "notes": "Amazon Nova Pro 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nova-lite-2",
      "name": "Nova Lite 2",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 0.07,
      "outputPricePerM": 0.28,
      "contextWindow": 300000,
      "notes": "Amazon Nova Lite 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nova-micro-2",
      "name": "Nova Micro 2",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 0.04,
      "outputPricePerM": 0.14,
      "contextWindow": 128000,
      "notes": "Amazon Nova Micro 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nova-canvas",
      "name": "Nova Canvas",
      "provider": "Amazon",
      "providerLogo": "amazon",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 128000,
      "notes": "Nova Canvas text gen",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "phi-5",
      "name": "Phi-5",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.4,
      "contextWindow": 128000,
      "notes": "Microsoft Phi-5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "phi-5-mini",
      "name": "Phi-5 Mini",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.2,
      "contextWindow": 128000,
      "notes": "Phi-5 Mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "phi-5-vision",
      "name": "Phi-5 Vision",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Phi-5 Vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mai-1",
      "name": "MAI-1",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 256000,
      "notes": "Microsoft MAI-1 flagship",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nemotron-4-340b",
      "name": "Nemotron-4 340B",
      "provider": "NVIDIA",
      "providerLogo": "nvidia",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "NVIDIA Nemotron",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nemotron-ultra-2",
      "name": "Nemotron Ultra 2",
      "provider": "NVIDIA",
      "providerLogo": "nvidia",
      "inputPricePerM": 3,
      "outputPricePerM": 9,
      "contextWindow": 256000,
      "notes": "Nemotron Ultra 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nemotron-nano-2",
      "name": "Nemotron Nano 2",
      "provider": "NVIDIA",
      "providerLogo": "nvidia",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "Nemotron Nano",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "granite-4-instruct",
      "name": "Granite 4 Instruct",
      "provider": "IBM",
      "providerLogo": "ibm",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "IBM Granite 4",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "granite-4-code",
      "name": "Granite 4 Code",
      "provider": "IBM",
      "providerLogo": "ibm",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Granite 4 Code",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yi-3-large",
      "name": "Yi-3 Large",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 200000,
      "notes": "Yi-3 Large",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yi-3-medium",
      "name": "Yi-3 Medium",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 200000,
      "notes": "Yi-3 Medium",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yi-3-vision",
      "name": "Yi-3 Vision",
      "provider": "01.AI",
      "providerLogo": "01ai",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Yi-3 Vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "minimax-text-02",
      "name": "MiniMax Text-02",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "MiniMax Text 02",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "minimax-vl-02",
      "name": "MiniMax VL-02",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "MiniMax VL 02",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "reka-core-2",
      "name": "Reka Core 2",
      "provider": "Reka",
      "providerLogo": "reka",
      "inputPricePerM": 3,
      "outputPricePerM": 10,
      "contextWindow": 128000,
      "notes": "Reka Core 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "reka-flash-2",
      "name": "Reka Flash 2",
      "provider": "Reka",
      "providerLogo": "reka",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Reka Flash 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "jamba-2-large",
      "name": "Jamba 2 Large",
      "provider": "AI21",
      "providerLogo": "ai21",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 512000,
      "notes": "AI21 Jamba 2 Large",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "jamba-2-mini",
      "name": "Jamba 2 Mini",
      "provider": "AI21",
      "providerLogo": "ai21",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.4,
      "contextWindow": 512000,
      "notes": "AI21 Jamba 2 Mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "stable-lm-3",
      "name": "Stable LM 3",
      "provider": "Stability AI",
      "providerLogo": "stability",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "Stable LM 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "inflection-pi-3",
      "name": "Pi 3",
      "provider": "Inflection",
      "providerLogo": "inflection",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 128000,
      "notes": "Inflection Pi 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "dbrx-2",
      "name": "DBRX 2",
      "provider": "Databricks",
      "providerLogo": "databricks",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 256000,
      "notes": "Databricks DBRX 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "dbrx-instruct-2",
      "name": "DBRX Instruct 2",
      "provider": "Databricks",
      "providerLogo": "databricks",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 256000,
      "notes": "DBRX Instruct 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "arctic-2",
      "name": "Arctic 2",
      "provider": "Snowflake",
      "providerLogo": "snowflake",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 128000,
      "notes": "Snowflake Arctic 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hermes-4-405b",
      "name": "Hermes 4 405B",
      "provider": "Nous Research",
      "providerLogo": "nous-research",
      "inputPricePerM": 1.8,
      "outputPricePerM": 5.4,
      "contextWindow": 128000,
      "notes": "Nous Hermes 4 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hermes-4-70b",
      "name": "Hermes 4 70B",
      "provider": "Nous Research",
      "providerLogo": "nous-research",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Nous Hermes 4 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "falcon-3-180b",
      "name": "Falcon 3 180B",
      "provider": "TII",
      "providerLogo": "tii",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 128000,
      "notes": "TII Falcon 3 180B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "falcon-3-40b",
      "name": "Falcon 3 40B",
      "provider": "TII",
      "providerLogo": "tii",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "TII Falcon 3 40B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sakana-evo-2",
      "name": "Sakana Evo 2",
      "provider": "Sakana",
      "providerLogo": "sakana",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Sakana evolutionary model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hunyuan-large-2",
      "name": "Hunyuan Large 2",
      "provider": "Tencent",
      "providerLogo": "tencent",
      "inputPricePerM": 1.2,
      "outputPricePerM": 4,
      "contextWindow": 256000,
      "notes": "Tencent Hunyuan Large 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hunyuan-turbo-2",
      "name": "Hunyuan Turbo 2",
      "provider": "Tencent",
      "providerLogo": "tencent",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "Tencent Hunyuan Turbo",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "ernie-5",
      "name": "ERNIE 5",
      "provider": "Baidu",
      "providerLogo": "baidu",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Baidu ERNIE 5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "ernie-5-speed",
      "name": "ERNIE 5 Speed",
      "provider": "Baidu",
      "providerLogo": "baidu",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "ERNIE 5 Speed",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "ernie-5-lite",
      "name": "ERNIE 5 Lite",
      "provider": "Baidu",
      "providerLogo": "baidu",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "ERNIE 5 Lite",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "doubao-2-pro",
      "name": "Doubao 2 Pro",
      "provider": "ByteDance",
      "providerLogo": "bytedance",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 256000,
      "notes": "Doubao 2 Pro",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "doubao-2-lite",
      "name": "Doubao 2 Lite",
      "provider": "ByteDance",
      "providerLogo": "bytedance",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "Doubao 2 Lite",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "doubao-vision-2",
      "name": "Doubao Vision 2",
      "provider": "ByteDance",
      "providerLogo": "bytedance",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Doubao Vision 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "solar-pro-2",
      "name": "Solar Pro 2",
      "provider": "Upstage",
      "providerLogo": "upstage",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "Upstage Solar Pro 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "solar-mini-2",
      "name": "Solar Mini 2",
      "provider": "Upstage",
      "providerLogo": "upstage",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Upstage Solar Mini 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "exaone-4",
      "name": "EXAONE 4",
      "provider": "LG AI",
      "providerLogo": "lg",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "LG EXAONE 4",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "exaone-4-deep",
      "name": "EXAONE 4 Deep",
      "provider": "LG AI",
      "providerLogo": "lg",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "EXAONE 4 reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hyperclova-x-2",
      "name": "HyperCLOVA X 2",
      "provider": "Naver",
      "providerLogo": "naver",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 128000,
      "notes": "Naver HyperCLOVA X 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yuan-3",
      "name": "Yuan 3",
      "provider": "Inspur",
      "providerLogo": "inspur",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Inspur Yuan 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gigachat-3",
      "name": "GigaChat 3",
      "provider": "Sber",
      "providerLogo": "sber",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Sber GigaChat 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yandexgpt-5-pro",
      "name": "YandexGPT 5 Pro",
      "provider": "Yandex",
      "providerLogo": "yandex",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 128000,
      "notes": "YandexGPT 5 Pro",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "yandexgpt-5-lite",
      "name": "YandexGPT 5 Lite",
      "provider": "Yandex",
      "providerLogo": "yandex",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "YandexGPT 5 Lite",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "olmo-3-13b",
      "name": "OLMo 3 13B",
      "provider": "Allen AI",
      "providerLogo": "allenai",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 128000,
      "notes": "Allen AI OLMo 3 13B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "olmo-3-70b",
      "name": "OLMo 3 70B",
      "provider": "Allen AI",
      "providerLogo": "allenai",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "OLMo 3 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "tulu-3-405b",
      "name": "Tulu 3 405B",
      "provider": "Allen AI",
      "providerLogo": "allenai",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Allen AI Tulu 3 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "internlm-3",
      "name": "InternLM 3",
      "provider": "Shanghai AI Lab",
      "providerLogo": "internlm",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "InternLM 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "internvl-3",
      "name": "InternVL 3",
      "provider": "Shanghai AI Lab",
      "providerLogo": "internlm",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "InternVL 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "pangu-5",
      "name": "Pangu 5",
      "provider": "Huawei",
      "providerLogo": "huawei",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Huawei Pangu 5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sarvam-2",
      "name": "Sarvam 2",
      "provider": "Sarvam",
      "providerLogo": "sarvam",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Sarvam 2 Indic",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "openrouter-auto",
      "name": "OpenRouter Auto",
      "provider": "OpenRouter",
      "providerLogo": "openrouter",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 200000,
      "notes": "OpenRouter auto routing",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "openrouter-owl-alpha",
      "name": "Owl Alpha",
      "provider": "OpenRouter",
      "providerLogo": "openrouter",
      "inputPricePerM": 0,
      "outputPricePerM": 0,
      "contextWindow": 1048756,
      "notes": "Free alpha — high-performance agentic foundation model with native tool use and ~1.05M context. Prompts/completions may be logged.",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-20"
    },
    {
      "id": "together-llama-5-70b",
      "name": "Llama 5 70B (Together)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 256000,
      "notes": "Together-hosted Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "together-qwen3-coder",
      "name": "Qwen3 Coder (Together)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 256000,
      "notes": "Together-hosted Qwen3 Coder",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "together-deepseek-r2",
      "name": "DeepSeek R2 (Together)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.8,
      "contextWindow": 128000,
      "notes": "Together-hosted DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "fireworks-llama-5-70b",
      "name": "Llama 5 70B (Fireworks)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 256000,
      "notes": "Fireworks Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "fireworks-deepseek-r2",
      "name": "DeepSeek R2 (Fireworks)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.75,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Fireworks DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "fireworks-qwen3-coder",
      "name": "Qwen3 Coder (Fireworks)",
      "provider": "Fireworks AI",
      "providerLogo": "fireworks",
      "inputPricePerM": 0.9,
      "outputPricePerM": 2.7,
      "contextWindow": 256000,
      "notes": "Fireworks Qwen3 Coder",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "groq-llama-5-70b",
      "name": "Llama 5 70B (Groq)",
      "provider": "Groq",
      "providerLogo": "groq",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "Groq-hosted Llama 5 70B fast",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "groq-llama-4-maverick",
      "name": "Llama 4 Maverick (Groq)",
      "provider": "Groq",
      "providerLogo": "groq",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 1000000,
      "notes": "Groq Llama 4 Maverick",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "groq-deepseek-r2",
      "name": "DeepSeek R2 (Groq)",
      "provider": "Groq",
      "providerLogo": "groq",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.7,
      "contextWindow": 128000,
      "notes": "Groq DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "groq-kimi-k2",
      "name": "Kimi K2 (Groq)",
      "provider": "Groq",
      "providerLogo": "groq",
      "inputPricePerM": 0.9,
      "outputPricePerM": 2.7,
      "contextWindow": 1000000,
      "notes": "Groq Kimi K2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "groq-qwen3-32b",
      "name": "Qwen3 32B (Groq)",
      "provider": "Groq",
      "providerLogo": "groq",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 256000,
      "notes": "Groq Qwen3 32B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "cerebras-llama-5-70b",
      "name": "Llama 5 70B (Cerebras)",
      "provider": "Cerebras",
      "providerLogo": "cerebras",
      "inputPricePerM": 0.65,
      "outputPricePerM": 1.95,
      "contextWindow": 256000,
      "notes": "Cerebras Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "cerebras-llama-4-maverick",
      "name": "Llama 4 Maverick (Cerebras)",
      "provider": "Cerebras",
      "providerLogo": "cerebras",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 1000000,
      "notes": "Cerebras Llama 4 Maverick",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "cerebras-deepseek-r2",
      "name": "DeepSeek R2 (Cerebras)",
      "provider": "Cerebras",
      "providerLogo": "cerebras",
      "inputPricePerM": 0.85,
      "outputPricePerM": 3.4,
      "contextWindow": 128000,
      "notes": "Cerebras DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "cerebras-qwen3-32b",
      "name": "Qwen3 32B (Cerebras)",
      "provider": "Cerebras",
      "providerLogo": "cerebras",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "Cerebras Qwen3 32B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sambanova-llama-5-405b",
      "name": "Llama 5 405B (SambaNova)",
      "provider": "SambaNova",
      "providerLogo": "sambanova",
      "inputPricePerM": 2.5,
      "outputPricePerM": 7.5,
      "contextWindow": 256000,
      "notes": "SambaNova Llama 5 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sambanova-deepseek-r2",
      "name": "DeepSeek R2 (SambaNova)",
      "provider": "SambaNova",
      "providerLogo": "sambanova",
      "inputPricePerM": 0.9,
      "outputPricePerM": 3.6,
      "contextWindow": 128000,
      "notes": "SambaNova DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sambanova-qwen3-coder",
      "name": "Qwen3 Coder (SambaNova)",
      "provider": "SambaNova",
      "providerLogo": "sambanova",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 256000,
      "notes": "SambaNova Qwen3 Coder",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepinfra-llama-5-70b",
      "name": "Llama 5 70B (DeepInfra)",
      "provider": "DeepInfra",
      "providerLogo": "deepinfra",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "DeepInfra Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepinfra-qwen3-235b",
      "name": "Qwen3 235B (DeepInfra)",
      "provider": "DeepInfra",
      "providerLogo": "deepinfra",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 256000,
      "notes": "DeepInfra Qwen3 235B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deepinfra-mixtral-8x22b",
      "name": "Mixtral 8x22B (DeepInfra)",
      "provider": "DeepInfra",
      "providerLogo": "deepinfra",
      "inputPricePerM": 0.7,
      "outputPricePerM": 0.7,
      "contextWindow": 64000,
      "notes": "DeepInfra Mixtral 8x22B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "replicate-llama-5-70b",
      "name": "Llama 5 70B (Replicate)",
      "provider": "Replicate",
      "providerLogo": "replicate",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.1,
      "contextWindow": 256000,
      "notes": "Replicate Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "anyscale-llama-5-70b",
      "name": "Llama 5 70B (Anyscale)",
      "provider": "Anyscale",
      "providerLogo": "anyscale",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 256000,
      "notes": "Anyscale Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "anyscale-mixtral-8x22b",
      "name": "Mixtral 8x22B (Anyscale)",
      "provider": "Anyscale",
      "providerLogo": "anyscale",
      "inputPricePerM": 0.9,
      "outputPricePerM": 0.9,
      "contextWindow": 64000,
      "notes": "Anyscale Mixtral 8x22B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "lepton-llama-5-70b",
      "name": "Llama 5 70B (Lepton)",
      "provider": "Lepton AI",
      "providerLogo": "lepton",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.1,
      "contextWindow": 256000,
      "notes": "Lepton Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "octoai-llama-5-70b",
      "name": "Llama 5 70B (OctoAI)",
      "provider": "OctoAI",
      "providerLogo": "octoai",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.1,
      "contextWindow": 256000,
      "notes": "OctoAI Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hyperbolic-llama-5-405b",
      "name": "Llama 5 405B (Hyperbolic)",
      "provider": "Hyperbolic",
      "providerLogo": "hyperbolic",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Hyperbolic Llama 5 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hyperbolic-deepseek-v4",
      "name": "DeepSeek V4 (Hyperbolic)",
      "provider": "Hyperbolic",
      "providerLogo": "hyperbolic",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Hyperbolic DeepSeek V4",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "novita-llama-5-70b",
      "name": "Llama 5 70B (Novita)",
      "provider": "Novita AI",
      "providerLogo": "novita",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "Novita Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "novita-qwen3-235b",
      "name": "Qwen3 235B (Novita)",
      "provider": "Novita AI",
      "providerLogo": "novita",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 256000,
      "notes": "Novita Qwen3 235B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nebius-llama-5-70b",
      "name": "Llama 5 70B (Nebius)",
      "provider": "Nebius",
      "providerLogo": "nebius",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 256000,
      "notes": "Nebius Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "nebius-deepseek-r2",
      "name": "DeepSeek R2 (Nebius)",
      "provider": "Nebius",
      "providerLogo": "nebius",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.8,
      "contextWindow": 128000,
      "notes": "Nebius DeepSeek R2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 4,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "friendli-llama-5-70b",
      "name": "Llama 5 70B (Friendli)",
      "provider": "Friendli",
      "providerLogo": "friendli",
      "inputPricePerM": 0.55,
      "outputPricePerM": 1.65,
      "contextWindow": 256000,
      "notes": "Friendli Llama 5 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "lambda-llama-5-405b",
      "name": "Llama 5 405B (Lambda)",
      "provider": "Lambda",
      "providerLogo": "lambda",
      "inputPricePerM": 2.4,
      "outputPricePerM": 7.2,
      "contextWindow": 256000,
      "notes": "Lambda Llama 5 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "featherless-hermes-4-70b",
      "name": "Hermes 4 70B (Featherless)",
      "provider": "Featherless",
      "providerLogo": "featherless",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.1,
      "contextWindow": 128000,
      "notes": "Featherless Hermes 4 70B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "krutrim-2",
      "name": "Krutrim 2",
      "provider": "Krutrim",
      "providerLogo": "krutrim",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Krutrim 2 Indic LLM",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "pharia-2",
      "name": "Pharia 2",
      "provider": "Aleph Alpha",
      "providerLogo": "aleph-alpha",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Aleph Alpha Pharia 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mathstral-2",
      "name": "Mathstral 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "Mathstral 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "devstral-2",
      "name": "Devstral 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 256000,
      "notes": "Devstral 2 coding",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-realtime-2",
      "name": "GPT Realtime 2",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 4,
      "outputPricePerM": 16,
      "contextWindow": 128000,
      "notes": "OpenAI realtime audio+text",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gemini-3-computer-use",
      "name": "Gemini 3 Computer Use",
      "provider": "Google",
      "providerLogo": "google",
      "inputPricePerM": 3,
      "outputPricePerM": 12,
      "contextWindow": 1000000,
      "notes": "Gemini computer-use agent",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-computer-use",
      "name": "Claude 5 Computer Use",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 4,
      "outputPricePerM": 20,
      "contextWindow": 500000,
      "notes": "Claude computer-use agent",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "step-2",
      "name": "Step-2",
      "provider": "StepFun",
      "providerLogo": "stepfun",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 256000,
      "notes": "StepFun Step-2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "step-2v",
      "name": "Step-2V",
      "provider": "StepFun",
      "providerLogo": "stepfun",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "StepFun vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "skywork-4",
      "name": "Skywork 4",
      "provider": "Skywork",
      "providerLogo": "skywork",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Skywork 4",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "spark-5",
      "name": "Spark 5",
      "provider": "iFlyTek",
      "providerLogo": "iflytek",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "iFlyTek Spark 5",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "chatglm-4-plus",
      "name": "ChatGLM 4 Plus",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "ChatGLM 4 Plus",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "sensechat-6",
      "name": "SenseChat 6",
      "provider": "SenseTime",
      "providerLogo": "sensetime",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "SenseTime SenseChat 6",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "welm-2",
      "name": "WeLM 2",
      "provider": "Tencent",
      "providerLogo": "tencent",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Tencent WeLM 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-3.7-haiku",
      "name": "Claude 3.7 Haiku",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 0.7,
      "outputPricePerM": 3.5,
      "contextWindow": 200000,
      "notes": "Claude 3.7 Haiku",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-realtime-2-mini",
      "name": "GPT Realtime 2 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "OpenAI realtime mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "aya-vision-32b",
      "name": "Aya Vision 32B",
      "provider": "Cohere",
      "providerLogo": "cohere",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Aya Vision",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5-coder",
      "name": "GLM-5 Coder",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "GLM-5 Coder",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "minicpm-4",
      "name": "MiniCPM 4",
      "provider": "OpenBMB",
      "providerLogo": "openbmb",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "MiniCPM 4 edge",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "phind-70b-2",
      "name": "Phind 70B v2",
      "provider": "Phind",
      "providerLogo": "phind",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Phind code 70B v2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "wizardlm-3",
      "name": "WizardLM 3",
      "provider": "WizardLM",
      "providerLogo": "wizardlm",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "WizardLM 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "orca-3",
      "name": "Orca 3",
      "provider": "Microsoft",
      "providerLogo": "microsoft",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 128000,
      "notes": "Microsoft Orca 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-medium-3-latest",
      "name": "Mistral Medium 3 Latest",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 256000,
      "notes": "Mistral Medium 3 latest pointer",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-5.7",
      "name": "GPT-5.7",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 3,
      "outputPricePerM": 12,
      "contextWindow": 500000,
      "notes": "OpenAI GPT-5.7",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-5.7-mini",
      "name": "GPT-5.7 Mini",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 500000,
      "notes": "OpenAI GPT-5.7 Mini",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hailuo-text-2",
      "name": "Hailuo Text 2",
      "provider": "MiniMax",
      "providerLogo": "minimax",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 256000,
      "notes": "Hailuo text model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "stable-code-3b-2",
      "name": "Stable Code 3B v2",
      "provider": "Stability AI",
      "providerLogo": "stability",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.15,
      "contextWindow": 128000,
      "notes": "Stable Code 3B v2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-nemotron-super-2",
      "name": "Llama Nemotron Super 2",
      "provider": "NVIDIA",
      "providerLogo": "nvidia",
      "inputPricePerM": 0.7,
      "outputPricePerM": 2.1,
      "contextWindow": 128000,
      "notes": "NVIDIA Llama Nemotron Super 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "llama-nemotron-nano-2",
      "name": "Llama Nemotron Nano 2",
      "provider": "NVIDIA",
      "providerLogo": "nvidia",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "NVIDIA Llama Nemotron Nano 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "together-cogito-v2",
      "name": "Cogito v2 (Together)",
      "provider": "Together AI",
      "providerLogo": "together",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 128000,
      "notes": "Together-hosted Cogito v2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "inception-mercury",
      "name": "Mercury",
      "provider": "Inception Labs",
      "providerLogo": "inception",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Diffusion LLM Mercury",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "inception-mercury-coder",
      "name": "Mercury Coder",
      "provider": "Inception Labs",
      "providerLogo": "inception",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 128000,
      "notes": "Diffusion LLM Mercury Coder",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "liquid-lfm-2-40b",
      "name": "LFM 2 40B",
      "provider": "Liquid AI",
      "providerLogo": "liquid",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Liquid LFM 2 40B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "liquid-lfm-2-7b",
      "name": "LFM 2 7B",
      "provider": "Liquid AI",
      "providerLogo": "liquid",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.45,
      "contextWindow": 128000,
      "notes": "Liquid LFM 2 7B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mosaic-mpt-2-30b",
      "name": "MPT 2 30B",
      "provider": "MosaicML",
      "providerLogo": "mosaic",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "MosaicML MPT 2 30B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "refuel-llm-3",
      "name": "Refuel LLM 3",
      "provider": "Refuel",
      "providerLogo": "refuel",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 128000,
      "notes": "Refuel LLM 3",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-saba-2",
      "name": "Mistral Saba 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Mistral Saba 2 MENA",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "deephermes-3-405b",
      "name": "DeepHermes 3 405B",
      "provider": "Nous Research",
      "providerLogo": "nous-research",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Nous DeepHermes 3 405B",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-3.7-sonnet-v2",
      "name": "Claude 3.7 Sonnet v2",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 3,
      "outputPricePerM": 15,
      "contextWindow": 200000,
      "notes": "Claude 3.7 Sonnet refresh",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-ocr-2",
      "name": "Mistral OCR 2",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 128000,
      "notes": "Mistral OCR 2",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "gpt-5.5-vision",
      "name": "GPT-5.5 Vision",
      "provider": "OpenAI",
      "providerLogo": "openai",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 400000,
      "notes": "GPT-5.5 vision-tuned",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "claude-5-batch",
      "name": "Claude 5 Sonnet Batch",
      "provider": "Anthropic",
      "providerLogo": "anthropic",
      "inputPricePerM": 2,
      "outputPricePerM": 10,
      "contextWindow": 1000000,
      "notes": "Claude 5 Sonnet batch tier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "glm-5-thinking",
      "name": "GLM-5 Thinking",
      "provider": "Zhipu",
      "providerLogo": "zhipu",
      "inputPricePerM": 2,
      "outputPricePerM": 8,
      "contextWindow": 256000,
      "notes": "GLM-5 thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "qwen3-max-thinking",
      "name": "Qwen3 Max Thinking",
      "provider": "Alibaba",
      "providerLogo": "qwen",
      "inputPricePerM": 3,
      "outputPricePerM": 12,
      "contextWindow": 1000000,
      "notes": "Qwen3 Max thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3.5,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "hunyuan-thinking",
      "name": "Hunyuan Thinking",
      "provider": "Tencent",
      "providerLogo": "tencent",
      "inputPricePerM": 1.8,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Hunyuan thinking mode",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "ernie-5-thinking",
      "name": "ERNIE 5 Thinking",
      "provider": "Baidu",
      "providerLogo": "baidu",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 256000,
      "notes": "ERNIE 5 thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "doubao-2-thinking",
      "name": "Doubao 2 Thinking",
      "provider": "ByteDance",
      "providerLogo": "bytedance",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 256000,
      "notes": "Doubao 2 thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "mistral-large-3-thinking",
      "name": "Mistral Large 3 Thinking",
      "provider": "Mistral",
      "providerLogo": "mistral",
      "inputPricePerM": 3.5,
      "outputPricePerM": 14,
      "contextWindow": 256000,
      "notes": "Mistral Large 3 thinking",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 3,
      "lastUpdated": "2026-06-13"
    },
    {
      "id": "palmyra-x5",
      "name": "Palmyra X5",
      "provider": "Writer",
      "providerLogo": "writer",
      "inputPricePerM": 0.6,
      "outputPricePerM": 6,
      "contextWindow": 1000000,
      "notes": "Enterprise-grade reasoning, agentic workflows",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "palmyra-x4",
      "name": "Palmyra X4",
      "provider": "Writer",
      "providerLogo": "writer",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 128000,
      "notes": "Tool-use and structured outputs for enterprise",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "palmyra-med-70b",
      "name": "Palmyra Med 70B",
      "provider": "Writer",
      "providerLogo": "writer",
      "inputPricePerM": 5,
      "outputPricePerM": 12,
      "contextWindow": 32000,
      "notes": "Medical-domain specialist model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "palmyra-fin-70b",
      "name": "Palmyra Fin 70B",
      "provider": "Writer",
      "providerLogo": "writer",
      "inputPricePerM": 5,
      "outputPricePerM": 12,
      "contextWindow": 32000,
      "notes": "Finance-domain specialist model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "palmyra-creative",
      "name": "Palmyra Creative",
      "provider": "Writer",
      "providerLogo": "writer",
      "inputPricePerM": 1.5,
      "outputPricePerM": 7.5,
      "contextWindow": 128000,
      "notes": "Marketing copy and long-form creative",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "nomic-chat-v2",
      "name": "Nomic Chat v2",
      "provider": "Nomic",
      "providerLogo": "nomic",
      "inputPricePerM": 0.25,
      "outputPricePerM": 0.75,
      "contextWindow": 32000,
      "notes": "Open-data chat model from Nomic",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "nomic-chat-v3",
      "name": "Nomic Chat v3",
      "provider": "Nomic",
      "providerLogo": "nomic",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 128000,
      "notes": "Successor with longer context and tool use",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "nomic-coder-15b",
      "name": "Nomic Coder 15B",
      "provider": "Nomic",
      "providerLogo": "nomic",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 64000,
      "notes": "Code-specialized open model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "nomic-reasoner-32b",
      "name": "Nomic Reasoner 32B",
      "provider": "Nomic",
      "providerLogo": "nomic",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 128000,
      "notes": "Reasoning-tuned open model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 2,
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "nomic-mini-3b",
      "name": "Nomic Mini 3B",
      "provider": "Nomic",
      "providerLogo": "nomic",
      "inputPricePerM": 0.08,
      "outputPricePerM": 0.24,
      "contextWindow": 32000,
      "notes": "On-device-class small open model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "contextual-clm-v2",
      "name": "Contextual CLM v2",
      "provider": "Contextual AI",
      "providerLogo": "contextual",
      "inputPricePerM": 1.5,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Grounded RAG language model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "contextual-clm-mini",
      "name": "Contextual CLM Mini",
      "provider": "Contextual AI",
      "providerLogo": "contextual",
      "inputPricePerM": 0.5,
      "outputPricePerM": 2,
      "contextWindow": 64000,
      "notes": "Cheaper RAG-tuned model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "contextual-clm-large",
      "name": "Contextual CLM Large",
      "provider": "Contextual AI",
      "providerLogo": "contextual",
      "inputPricePerM": 4,
      "outputPricePerM": 12,
      "contextWindow": 200000,
      "notes": "Premium grounded reasoning tier",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "contextual-rerank-2",
      "name": "Contextual Rerank 2",
      "provider": "Contextual AI",
      "providerLogo": "contextual",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.1,
      "contextWindow": 8000,
      "notes": "Reranker priced symmetrically per token",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "contextual-agent-1",
      "name": "Contextual Agent 1",
      "provider": "Contextual AI",
      "providerLogo": "contextual",
      "inputPricePerM": 2.5,
      "outputPricePerM": 10,
      "contextWindow": 128000,
      "notes": "Tool-using enterprise agent model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "character-chat-2",
      "name": "Character Chat 2",
      "provider": "Character.AI",
      "providerLogo": "character",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 32000,
      "notes": "Persona-driven dialogue model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "character-chat-2-mini",
      "name": "Character Chat 2 Mini",
      "provider": "Character.AI",
      "providerLogo": "character",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.45,
      "contextWindow": 16000,
      "notes": "Low-latency persona chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "character-creator",
      "name": "Character Creator",
      "provider": "Character.AI",
      "providerLogo": "character",
      "inputPricePerM": 0.8,
      "outputPricePerM": 2.4,
      "contextWindow": 64000,
      "notes": "Roleplay + worldbuilding model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "character-voice-llm",
      "name": "Character Voice LLM",
      "provider": "Character.AI",
      "providerLogo": "character",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 32000,
      "notes": "Voice-companion tuned LLM",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "character-pro",
      "name": "Character Pro",
      "provider": "Character.AI",
      "providerLogo": "character",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Higher-quality persona reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "arcee-spark",
      "name": "Arcee Spark",
      "provider": "Arcee AI",
      "providerLogo": "arcee",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 32000,
      "notes": "Small merge-based general model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "arcee-nova",
      "name": "Arcee Nova",
      "provider": "Arcee AI",
      "providerLogo": "arcee",
      "inputPricePerM": 0.45,
      "outputPricePerM": 1.35,
      "contextWindow": 128000,
      "notes": "Flagship MergeKit-derived model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "arcee-agent",
      "name": "Arcee Agent",
      "provider": "Arcee AI",
      "providerLogo": "arcee",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 64000,
      "notes": "Function-calling tuned model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "arcee-scribe",
      "name": "Arcee Scribe",
      "provider": "Arcee AI",
      "providerLogo": "arcee",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 200000,
      "notes": "Long-context summarization specialist",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "arcee-coder",
      "name": "Arcee Coder",
      "provider": "Arcee AI",
      "providerLogo": "arcee",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 64000,
      "notes": "Code-merge model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "h2o-danube3-4b",
      "name": "H2O Danube3 4B",
      "provider": "H2O.ai",
      "providerLogo": "h2o",
      "inputPricePerM": 0.08,
      "outputPricePerM": 0.24,
      "contextWindow": 16000,
      "notes": "Compact open chat model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "h2ogpt-oasst-70b",
      "name": "h2oGPT OASST 70B",
      "provider": "H2O.ai",
      "providerLogo": "h2o",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 32000,
      "notes": "Enterprise open assistant",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "h2o-doc-llm",
      "name": "H2O Document LLM",
      "provider": "H2O.ai",
      "providerLogo": "h2o",
      "inputPricePerM": 1,
      "outputPricePerM": 3,
      "contextWindow": 200000,
      "notes": "Long-context document Q&A",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "h2o-agent-1",
      "name": "H2O Agent 1",
      "provider": "H2O.ai",
      "providerLogo": "h2o",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 128000,
      "notes": "Enterprise agent runtime model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "h2o-mini-1b",
      "name": "H2O Mini 1B",
      "provider": "H2O.ai",
      "providerLogo": "h2o",
      "inputPricePerM": 0.03,
      "outputPricePerM": 0.1,
      "contextWindow": 8000,
      "notes": "Edge-class tiny model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "kakao-kanana-flash",
      "name": "Kanana Flash",
      "provider": "Kakao",
      "providerLogo": "kakao",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 32000,
      "notes": "Korean-first fast chat model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "kakao-kanana-pro",
      "name": "Kanana Pro",
      "provider": "Kakao",
      "providerLogo": "kakao",
      "inputPricePerM": 1.2,
      "outputPricePerM": 3.6,
      "contextWindow": 128000,
      "notes": "Korean-first flagship model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "kakao-kanana-nano",
      "name": "Kanana Nano",
      "provider": "Kakao",
      "providerLogo": "kakao",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.15,
      "contextWindow": 16000,
      "notes": "Low-cost Korean classification + chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "kakao-kanana-vision",
      "name": "Kanana Vision",
      "provider": "Kakao",
      "providerLogo": "kakao",
      "inputPricePerM": 1.5,
      "outputPricePerM": 4.5,
      "contextWindow": 64000,
      "notes": "Korean multimodal chat",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "kakao-kogpt-2",
      "name": "KoGPT 2",
      "provider": "Kakao",
      "providerLogo": "kakao",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 32000,
      "notes": "Successor to original KoGPT",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "varco-llm-13b",
      "name": "VARCO LLM 13B",
      "provider": "NCSoft",
      "providerLogo": "ncsoft",
      "inputPricePerM": 0.5,
      "outputPricePerM": 1.5,
      "contextWindow": 32000,
      "notes": "Korean enterprise model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "varco-llm-70b",
      "name": "VARCO LLM 70B",
      "provider": "NCSoft",
      "providerLogo": "ncsoft",
      "inputPricePerM": 1.8,
      "outputPricePerM": 5.4,
      "contextWindow": 64000,
      "notes": "Flagship Korean enterprise model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "varco-mini-3b",
      "name": "VARCO Mini 3B",
      "provider": "NCSoft",
      "providerLogo": "ncsoft",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 16000,
      "notes": "Compact Korean model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "varco-coder",
      "name": "VARCO Coder",
      "provider": "NCSoft",
      "providerLogo": "ncsoft",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 32000,
      "notes": "Korean-aware coding model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "varco-agent",
      "name": "VARCO Agent",
      "provider": "NCSoft",
      "providerLogo": "ncsoft",
      "inputPricePerM": 2,
      "outputPricePerM": 6,
      "contextWindow": 128000,
      "notes": "Tool-using Korean agent",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "sea-lion-v3-9b",
      "name": "SEA-LION v3 9B",
      "provider": "AI Singapore",
      "providerLogo": "ai-singapore",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.45,
      "contextWindow": 32000,
      "notes": "Southeast Asian multilingual model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "sea-lion-v3-27b",
      "name": "SEA-LION v3 27B",
      "provider": "AI Singapore",
      "providerLogo": "ai-singapore",
      "inputPricePerM": 0.4,
      "outputPricePerM": 1.2,
      "contextWindow": 64000,
      "notes": "Larger SEA multilingual flagship",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "sea-lion-instruct",
      "name": "SEA-LION Instruct",
      "provider": "AI Singapore",
      "providerLogo": "ai-singapore",
      "inputPricePerM": 0.3,
      "outputPricePerM": 0.9,
      "contextWindow": 32000,
      "notes": "Instruction-tuned SEA model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "sea-lion-translate",
      "name": "SEA-LION Translate",
      "provider": "AI Singapore",
      "providerLogo": "ai-singapore",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 16000,
      "notes": "SEA translation specialist",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "sea-lion-reasoner",
      "name": "SEA-LION Reasoner",
      "provider": "AI Singapore",
      "providerLogo": "ai-singapore",
      "inputPricePerM": 0.6,
      "outputPricePerM": 1.8,
      "contextWindow": 64000,
      "notes": "Reasoning-tuned SEA model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 2,
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "pleias-1-3b",
      "name": "Pleias 1.3B",
      "provider": "Pleias",
      "providerLogo": "pleias",
      "inputPricePerM": 0.05,
      "outputPricePerM": 0.15,
      "contextWindow": 8000,
      "notes": "Fully open-data multilingual small model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "pleias-3b",
      "name": "Pleias 3B",
      "provider": "Pleias",
      "providerLogo": "pleias",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 16000,
      "notes": "Compliant-corpus open model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "pleias-7b",
      "name": "Pleias 7B",
      "provider": "Pleias",
      "providerLogo": "pleias",
      "inputPricePerM": 0.2,
      "outputPricePerM": 0.6,
      "contextWindow": 32000,
      "notes": "Mid-size open-data model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "pleias-rag-7b",
      "name": "Pleias RAG 7B",
      "provider": "Pleias",
      "providerLogo": "pleias",
      "inputPricePerM": 0.25,
      "outputPricePerM": 0.75,
      "contextWindow": 32000,
      "notes": "Citation-friendly RAG model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "pleias-translate",
      "name": "Pleias Translate",
      "provider": "Pleias",
      "providerLogo": "pleias",
      "inputPricePerM": 0.15,
      "outputPricePerM": 0.45,
      "contextWindow": 16000,
      "notes": "Open-data translation model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-06-21"
    },
    {
      "id": "ling-3.0-flash",
      "name": "Ling-3.0-flash",
      "provider": "Ant Ling",
      "providerLogo": "antling",
      "inputPricePerM": 0.06,
      "outputPricePerM": 0.18,
      "contextWindow": 128000,
      "notes": "High-speed lightweight agentic model; 500K free tokens/day",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-08-09"
    },
    {
      "id": "ling-2.6-flash",
      "name": "Ling-2.6-flash",
      "provider": "Ant Ling",
      "providerLogo": "antling",
      "inputPricePerM": 0.1,
      "outputPricePerM": 0.3,
      "contextWindow": 128000,
      "notes": "Low-cost agent execution model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-08-09"
    },
    {
      "id": "ling-2.6-1t",
      "name": "Ling-2.6-1T",
      "provider": "Ant Ling",
      "providerLogo": "antling",
      "inputPricePerM": 0.3,
      "outputPricePerM": 2.5,
      "contextWindow": 128000,
      "notes": "Flagship 1T-parameter MoE for heavy reasoning",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "lastUpdated": "2026-08-09"
    },
    {
      "id": "ring-2.6-1t",
      "name": "Ring-2.6-1T",
      "provider": "Ant Ling",
      "providerLogo": "antling",
      "inputPricePerM": 0.3,
      "outputPricePerM": 2.5,
      "contextWindow": 128000,
      "notes": "Deep reasoning & planning agent model",
      "batchDiscount": null,
      "deprecated": false,
      "tokenizer": "approx",
      "isReasoning": true,
      "reasoningRatio": 2,
      "lastUpdated": "2026-08-09"
    }
  ]
}