Should you use Mistral Large 3?
Mistral Large 3 is listed for chat workloads and supports a 256K context window.
Use it when Mistral AI's free tier is enough for evaluation, demos, or light production traffic.
https://api.mistral.ai/v1 mistral-large-3 | Benchmark | Score | Metric | Date |
|---|---|---|---|
| Artificial Analysis Coding Index | 22.7 | index | 2026-06-04 |
| SciCode | 36.2 | percent correct | 2026-06-04 |
| Terminal-Bench Hard | 15.9 | success rate | 2026-06-04 |
Mistral Large 3 is listed for chat workloads and supports a 256K context window.
Use it when Mistral AI's free tier is enough for evaluation, demos, or light production traffic.
We only found this Mistral Large 3 listing on Mistral AI in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Mistral Large 3 | Free tier | 256K | OpenAI-style | ~1 RPS, 500K TPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| Mistral 7B | Mistral AI | 33K | Free tier |
| Mixtral 8x7B | Mistral AI | 33K | Free tier |
| Mistral Medium 3.5 (128B) | Mistral AI | 256K | Free tier |
| Mistral Small 4 | Mistral AI | 256K | Free tier |
| Ministral 8B | Mistral AI | 256K | Free tier |
Mistral Large 3 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Mistral Large 3 is listed with free API access on Mistral AI, subject to the provider's quota and account policy.
The model ID shown in this catalog is mistral-large-3.
The listed free tier limit is ~1 RPS, 500K TPM. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 256K tokens with up to 256K output tokens.
"Mistral AI's Large 3 model offers 256K token text generation, ideal for chat applications, with free access, no credit card needed, and OpenAI compatibility. Developers can utilize its advanced context handling, while being limited to ~1 RPS and 500K tokens/month."
For API keys, setup steps, and provider-level limits, see the Mistral AI provider page.