Provider pricing
Fireworks AI AI API pricing
Fireworks AI runs open-weight models on a custom inference stack (FireAttention, speculative decoding) that delivers some of the lowest latencies in the industry. The catalog covers Llama 4, DeepSeek V4, Qwen3, Mixtral, and Nemotron, plus image, audio, and embedding models — all behind an OpenAI-compatible API.
Founded2022
HeadquartersRedwood City, CA
Tracked models8
Best for
Latency-sensitive production workloads on open-weight models — agents, voice, real-time chat.
Strengths
- Industry-leading latency via FireAttention + speculative decoding
- Function calling, JSON mode, and structured output on open-weight models
- On-demand fine-tuning + LoRA serving at no extra inference cost
- Compound AI: chain models, retrieval, and tools server-side
Tracked Fireworks AI models
| Model | Input $/M | Output $/M | Context | Tier | Best for |
|---|---|---|---|---|---|
| Llama 4 Scout (Fireworks AI) | $0.090 | $0.250 | 1,000,000 | Budget | Fireworks-hosted Llama 4 Scout — ultra-fast inference |
| Llama 4 Maverick (Fireworks AI) | $0.180 | $0.500 | 1,000,000 | Mid-tier | Fireworks-hosted Llama 4 Maverick — low-latency reasoning |
| Qwen3 32B (Fireworks AI) | $0.250 | $0.700 | 128,000 | Mid-tier | Fireworks-hosted Qwen3 32B optimized for throughput |
| Mixtral 8x22B (Fireworks AI) | $1.80 | $5.40 | 64,000 | Flagship | Fireworks-hosted Mixtral 8x22B with speculative decoding |
| Mistral Small 3.1 (Fireworks AI) | $0.130 | $0.500 | 128,000 | Budget | Fireworks-hosted Mistral Small 3.1 for high-volume agents |
| Llama 3.3 70B (Fireworks AI) | $0.900 | $0.900 | 128,000 | Mid-tier | Fireworks-hosted Llama 3.3 70B — low-latency inference |
| DeepSeek R1 (Fireworks AI) | $3.00 | $8.00 | 128,000 | Reasoning | Fireworks-hosted DeepSeek R1 with optimized throughput |
| Qwen 2.5 Coder 32B (Fireworks AI) | $0.900 | $0.900 | 131,072 | Mid-tier | Fireworks-hosted Qwen 2.5 Coder 32B for agentic dev tools |