Mistral Medium 3.1
Mistral Medium 3.1 was the top MT-Bench tier at Mistral AI's La Plateforme launch (8.6), with multilingual output across English, French, Italian, German, Spanish, and code.
import { streamText } from 'ai'
const result = streamText({ model: 'mistral/mistral-medium', prompt: 'Why is the sky blue?'})Playground
Try out Mistral Medium 3.1 by Mistral AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Mistral Medium 3.1
Ask Mistral Medium 3.1 anything to try it out.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
Mistral AI | 128K | 0.3s | 86tps | $0.40/M | $2.00/M | — | — | 05/07/2025 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by Mistral AI
| Model |
|---|
| 256K | 0.9s | 16tps | $0.10/M | $0.30/M | — | — | | 12/09/2025 | |||||
| 256K | 1.6s | 52tps | $0.50/M | $1.50/M | — | — | | 12/02/2025 | |||||
| 256K | 0.3s | 118tps | $0.20/M | $0.20/M | — | — | +1 | | 12/02/2025 | ||||
| 128K | 0.3s | 138tps | $0.10/M | $0.10/M | — | — | | 10/16/2024 | |||||
| 32K | 0.4s | 147tps | $0.10/M | $0.30/M | — | — | | 09/17/2024 | |||||
| $0.10/M | — | — | | 12/11/2023 |
About Mistral Medium 3.1
Mistral Medium 3.1 launched as the top MT-Bench tier on La Plateforme, alongside Mistral-tiny (efficiency) and Mistral-small (balance). At release Mistral Medium 3.1 scored 8.6 on MT-Bench. Mistral AI described it as a prototype endpoint undergoing deployed testing.
Mistral Medium 3.1's capability profile centers on five major European languages (English, French, Italian, German, and Spanish) alongside code generation. This multilingual design, combined with its position above tiny and small in the launch lineup, made it the default choice for many European-language workloads in Mistral AI's earliest days.
Mistral AI's portfolio has expanded since then, but Mistral Medium 3.1 remains available for teams with established integrations or workflows built around its specific capability profile.
What To Consider When Choosing a Provider
- Configuration: Mistral Medium 3.1 covers English, French, Italian, German, Spanish, and code. This makes Mistral Medium 3.1 a fit for European teams needing a single model across languages.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use Mistral Medium 3.1
Best For
- Multilingual European output: Coherent generation across English, French, Italian, German, and Spanish
- Existing production integrations: Teams with deployments built on Mistral Medium 3.1
- Code generation with multilingual docs: Tasks combining code and European-language comments
- Validated benchmark profile: Applications where historical benchmarks are a known quantity
Consider Alternatives When
- Higher capability general-purpose: You need a newer Mistral AI model (consider Mistral AI Large 3)
- Mathematical or structured reasoning: Tasks that require explicit reasoning traces (consider Magistral models)
- Vision input support: You need multimodal input (consider Pixtral models)
- Paramount cost efficiency: Cost dominates selection (consider Ministral or Mistral AI Small)
Conclusion
Mistral Medium 3.1 was Mistral AI's top MT-Bench launch endpoint. Mistral Medium 3.1 remains an option for European-language and code workloads tied to older integrations.