Skip to content
Mistral

Mistral Medium 3.1

Mistral Medium 3.1 was the top MT-Bench tier at Mistral's La Plateforme launch (8.6), with multilingual output across English, French, Italian, German, Spanish, and code.

View API reference
Input and output price
Input $0.40, Output $2, Per 1M tokens
24h uptime
Loading AI Gateway uptime
Get API keyRead the docs
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/mistral-medium',
  prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingPlayground

Try out Mistral Medium 3.1 by Mistral. 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 logo
mistral logo

Mistral Medium 3.1

Copy link to headingProviders

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
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Free Tier
Release Date
Mistral
Legal:Terms•Privacy
128K64K0.3 s
$0.40/M
$2/M
—
05/07/2025

Copy link to headingUptime

Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.

Copy link to headingThroughput

P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.

Copy link to headingLatency

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.

Getting started

Call Mistral Medium 3.1 through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.

Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.

index.ts
import { generateText } from 'ai';
import 'dotenv/config';


async function main() {
  const result = await generateText({
    model: 'mistral/mistral-medium',
    prompt: 'Why is the sky blue?',
  });


  console.log(result.text);
}


main().catch(console.error);

Top-level parameters

The same Mistral Medium 3.1 request in each API format AI Gateway supports.

top-level-params.ts
import { generateText } from 'ai';
import 'dotenv/config';


async function main() {
  const result = await generateText({
    model: 'mistral/mistral-medium',
    system: 'You are a concise technical assistant.',
    prompt: 'Summarize the tradeoffs between static generation and SSR.',
    maxOutputTokens: 1024,
    temperature: 0.5,
  });


  console.log(result.text);
}


main().catch(console.error);

Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. mistral/mistral-medium. AI Gateway routes the request to an available provider.
maxOutputTokensnumberNoHard cap on generated tokens. Mistral Medium 3.1 supports up to 64,000 output tokens.
providerOptionsRecord<string, JSONValue>NoAI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below.

Input limits

InputFormatsSourcesMax countMax sizeLimits
Text————Prompt and response share the 128K-token context window
Image—URL, base64, Uint8Array——Sent as image parts in messages; counts as input tokens

Provider options

Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.

Learn more in the AI SDK mistral provider docs.

provider-options.ts
import { generateText } from 'ai';
import 'dotenv/config';


async function main() {
  const result = await generateText({
    model: 'mistral/mistral-medium',
    prompt: 'Why is the sky blue?',
    providerOptions: {
      gateway: {
        only: ['mistral'],
      },
    },
  });


  console.log(result.text);
}


main().catch(console.error);

These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.

ParameterTypeRequiredDescription
providerOptions.gateway.onlystring[]NoRestrict routing to these provider slugs. Requests fail over only within the listed providers.
providerOptions.gateway.orderstring[]NoPreferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks.
providerOptions.gateway.sort'cost' | 'ttft' | 'tps'NoRank candidate providers by price, time to first token, or tokens per second instead of the default routing order.
providerOptions.gateway.zeroDataRetentionbooleanNoRoute only to providers with a zero-data-retention policy for this model.

Routing across providers

AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.

Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.

Image input

Send images alongside text as message parts. Images count as input tokens.

image-input.ts
import { generateText } from 'ai';
import 'dotenv/config';


async function main() {
  const result = await generateText({
    model: 'mistral/mistral-medium',
    messages: [
      {
        role: 'user',
        content: [
          { type: 'text', text: 'Describe this image.' },
          { type: 'image', image: 'https://example.com/photo.jpg' },
        ],
      },
    ],
  });


  console.log(result.text);
}


main().catch(console.error);

Tool calling

Expose tools the model can call. Define each tool’s inputs with a Zod schema.

tool-calling.ts
import { generateText, tool } from 'ai';
import { z } from 'zod';
import 'dotenv/config';


async function main() {
  const result = await generateText({
    model: 'mistral/mistral-medium',
    prompt: 'What is the weather in San Francisco?',
    tools: {
      getWeather: tool({
        description: 'Get the current weather for a location',
        inputSchema: z.object({ location: z.string() }),
        execute: async ({ location }) => ({ location, temperatureC: 18 }),
      }),
    },
  });


  console.log(result.text);
}


main().catch(console.error);

Copy link to headingMore models by Mistral

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Free Tier
Release Date
mistral/mistral-large-3
256K0.5 s80 tps
$0.50/M
$1.50/M
—
mistral logo
12/02/2025
mistral/ministral-14b
256K0.3 s113 tps
$0.20/M
$0.20/M
—
mistral logo
12/02/2025
mistral/codestral-embed
—
$0.15/M
—
mistral logo
05/28/2025
mistral/ministral-3b
128K0.3 s253 tps
$0.10/M
$0.10/M
—
mistral logo
10/16/2024
mistral/mistral-small
32K0.3 s28 tps
$0.10/M
$0.30/M
—
mistral logo
09/17/2024
mistral/mistral-embed
—
$0.10/M
—
mistral logo
12/11/2023

Copy link to headingAbout 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 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's earliest days.

Mistral'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.

Copy link to headingWhat 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: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
  • Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.

Copy link to headingWhen 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 model (consider Mistral 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 Small)

Copy link to headingConclusion

Mistral Medium 3.1 was Mistral's top MT-Bench launch endpoint. Mistral Medium 3.1 remains an option for European-language and code workloads tied to older integrations.

Copy link to headingFrequently Asked Questions

  • What was Mistral Medium 3.1's MT-Bench score?

    8.6 on MT-Bench at La Plateforme's launch, per Mistral's announcement.

  • What languages does Mistral Medium 3.1 support?

    English, French, Italian, German, Spanish, and code.

  • How does Mistral Medium 3.1 fit into the La Plateforme lineup?

    Mistral Medium 3.1 sat above Mistral-tiny (efficiency) and Mistral-small (balance) in Mistral's launch lineup and had the highest MT-Bench score of the three.

  • Is Mistral Medium 3.1 a good choice for new projects?

    For new projects, consider more recent models like Mistral Large 3 or Mistral Small. Mistral Medium 3.1 is most relevant for teams with existing integrations.

  • Does Mistral Medium 3.1 support function calling?

    Check the AI Gateway model capabilities documentation for documented capabilities. Function-calling support evolved across Mistral model generations.

  • What is the relationship between Mistral Medium 3.1 and Mistral Small?

    At La Plateforme's launch, Mistral Small occupied the balanced tier between tiny and medium. Mistral Small has since been updated (September 2024) while Medium retains its original profile.

  • How do I access Mistral Medium 3.1 through AI SDK?

    Use Mistral Medium 3.1 through AI Gateway via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

Your use is subject to Mistral's Terms & Privacy Policies.