Mistral's largest general model for enterprise agents, coding, and multilingual reasoningMistral Large 3 is offered by 16 providers on this page. Public prices are shown for 15 of them. Its official list price is $0.50 per 1M input tokens and $1.50 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 2.2× across the providers that host it.
Median output speed is 86 tokens per second, with 1.13s to the first token.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-11.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| MistralOfficial | First-party | $0.50 | $1.50 | $0.05 | — | 262,144 | 262,144 | |
| LLM Gateway | Gateway | $0.50 | $1.50 | — | — | 262,144 | 262,144 | |
| Amazon Bedrock mistral.mistral-large-3-675b-instruct | Cloud | $0.50 | $1.50 | — | — | 262,144 | 8,192 | |
| DevPass (LLM Gateway) | Gateway | $0.50 | $1.50 | — | — | 262,144 | 262,144 | |
| Merge Gateway | Gateway | $0.50 | $1.50 | $0.05 | — | 256,000 ⚠ | 256,000 | |
| OpenRouter | Gateway | $0.50 | $1.50 | $0.05 | — | 262,144 | 209,715 | |
| Opper | Gateway | $0.50 | $1.50 | — | — | 256,000 ⚠ | 8,192 | |
| Prime Inference | Gateway | $0.50 | $1.50 | — | — | 262,144 | 209,715 | |
| Eden AI | Gateway | $0.50 | $1.50 | $0.05 | — | 262,144 | 262,144 | |
| Kilo Gateway | Gateway | $0.50 | $1.50 | $0.05 | — | 262,144 | 209,715 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 22.7 | index | Source ↗ |
| SciCode | — | 36.2 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 15.9 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.