Model pricing
Llama 4 Scout (Together AI) pricing
Llama 4 Scout (Together AI) by Together AI costs $0.1 per 1M input tokens and $0.3 per 1M output tokens (cached input not recorded, batch input not recorded) as of 2026-06-11. A 1,000-input/500-output request costs $0.00025. The lowest-cost alternative with at least this context window and the same recorded reasoning category is GPT 4.1 Nano (OpenAI) at $0.05/$0.2; capability equivalence is not guaranteed.
Notes
Hosted open-weight inference — fast, affordable general purpose
Key pricing facts
| Fact | Value |
|---|---|
| Input / 1M tokens | $0.1 |
| Output / 1M tokens | $0.3 |
| Cached input / 1M | Not recorded |
| Batch input / output / 1M | Not recorded |
| Context window | 1,000,000 |
| Provider | Together AI |
| Last verified | 2026-06-11 |
| Snapshot updated | 2026-06-11 |
Last updated: · Source: Together AI pricing · Methodology
Frequently asked questions
What does Llama 4 Scout (Together AI) cost per million tokens?
Input costs $0.1 and output costs $0.3 per million tokens. The 1,000-input/500-output example costs $0.00025, before discounts, taxes, hidden reasoning tokens or context-tier surcharges.
Does Llama 4 Scout (Together AI) have cached or batch pricing?
Cached input: not separately recorded. Batch: not recorded in this dataset. Eligibility and cache-write charges depend on the provider; these discounts are not automatically stacked.
What is a cheaper alternative to Llama 4 Scout (Together AI)?
GPT 4.1 Nano (OpenAI) costs $0.05 input and $0.2 output per million tokens. This comparison matches context capacity and reasoning category, not benchmark quality. Test your workload before replacing a model.
How often are these prices verified?
The live pricing table synchronizes stored model records daily; public file snapshots update when the site is rebuilt. Synchronization is not independent provider verification. Snapshot updated 2026-06-11. The recorded model verification date is 2026-06-11.