Skip to content
Mistral

Mistral Large 3

Mistral Large 3 is a large-scale MoE model from Mistral, using a sparse mixture-of-experts architecture with 41B active parameters out of 675B total, the company's first MoE release since the Mixtral series.

View API reference
Input and output price
Input $0.50, Output $1.50, Per 1M tokens
24h uptime
Loading AI Gateway uptime
Get API keyRead the docs
import { streamText } from 'ai'


const result = streamText({
  model: 'mistral/mistral-large-3',
  prompt: 'Why is the sky blue?'
})
Read docs

Copy link to headingPlayground

Try out Mistral Large 3 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 Large 3

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
256K256K0.5 s81 tps
$0.50/M
$1.50/M
—
12/02/2025

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 Large 3 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-large-3',
    prompt: 'Why is the sky blue?',
  });


  console.log(result.text);
}


main().catch(console.error);

Top-level parameters

The same Mistral Large 3 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-large-3',
    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-large-3. AI Gateway routes the request to an available provider.
maxOutputTokensnumberNoHard cap on generated tokens. Mistral Large 3 supports up to 256,000 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 256K-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-large-3',
    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-large-3',
    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-large-3',
    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-medium-3.5
256K0.3 s
$1.50/M
$7.50/M
—
mistral logo
04/29/2026
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 Large 3

Announced December 2, 2025, Mistral Large 3 marks Mistral's return to the mixture-of-experts (MoE) architecture that defined their earlier Mixtral series, now at a larger scale. With 675B total parameters and 41B active per forward pass, Mistral Large 3 represents a substantial architectural evolution from the dense models that preceded it in the Large lineage.

The sparse MoE design lets Mistral Large 3 maintain inference efficiency comparable to a smaller dense model while drawing on a large total parameter pool for complex tasks. This architecture offers a tradeoff between capability and inference cost.

Through AI Gateway, you can access Mistral Large 3 without separate Mistral API credentials. Built-in observability gives you cost and latency visibility across every request.

Copy link to headingWhat To Consider When Choosing a Provider

  • Configuration: Mistral Large 3's return to MoE architecture brings sparse activation, where only part of the total parameters run per token, to Mistral's largest general-purpose open release as of the Mistral 3 announcement.
  • 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 Large 3

Best for

  • High-capability MoE tasks: Demanding Mistral's general-purpose MoE lineup
  • Complex reasoning and analysis: Tasks that benefit from a large total parameter pool
  • Long-form content generation: Long outputs where coherent multi-step logic has to hold across the whole piece
  • Mistral ecosystem fit: Applications that rely on its tooling, fine-tuning, or enterprise agreements
  • MoE inference efficiency: Workflows preferred over pure dense-model approaches

Consider alternatives when

  • Explicit chain-of-thought reasoning: Your task requires reasoning traces (consider Magistral Medium)
  • Primary cost constraint: Mistral Small or a Ministral variant meets accuracy requirements at lower per-token cost than the 675B flagship
  • Vision capabilities: You need multimodal input (consider Pixtral Large)

Copy link to headingConclusion

Mistral Large 3 brings back sparse MoE at a larger scale than Mixtral. For teams that want Mistral's largest general-purpose open MoE with 41B active parameters per forward pass, it fills that tier.

Copy link to headingFrequently Asked Questions

  • What is Mistral Large 3's architecture?

    A sparse mixture-of-experts (MoE) model with 675B total parameters and 41B active per forward pass.

  • Is this the first Mistral MoE model?

    No. Mistral describes Mistral Large 3 as the company's first MoE model since the Mixtral series, returning to sparse architecture at a larger scale.

  • When was Mistral Large 3 added to AI Gateway?

    December 2, 2025.

  • How does the MoE architecture affect inference cost?

    Only 41B of 675B total parameters activate per forward pass, so inference costs stay closer to a 41B dense model than a 675B dense model.

  • Does AI Gateway support BYOK for Mistral Large 3?

    Yes. AI Gateway supports Bring Your Own Key (BYOK) configuration. Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

  • How does Mistral Large 3 compare to Magistral Medium?

    Mistral Large 3 is the general-purpose MoE model in Mistral's lineup. Magistral Medium is a reasoning model with traceable chain-of-thought and published AIME 2024 scores. Pick Magistral Medium when you need explicit reasoning traces; pick Mistral Large 3 for general tasks without that requirement.

  • What observability does AI Gateway provide for Mistral Large 3?

    Request-level cost, latency, token counts, and provider routing decisions, without additional instrumentation.

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