Mistral Medium Latest
Mistral Medium Latest is Mistral's frontier-class multimodal model for agentic and coding work, merging instruction following, configurable reasoning, and coding into one dense 128B model with a context window of 262.1K tokens. Your use is subject to Mistral's Terms & Privacy Policies.
View API reference- Input and output price
- Input $1.50, Output $7.50, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'mistral/mistral-medium-3.5', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Mistral Medium Latest 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 Medium Latest
Mistral Medium Latest
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.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Mistral Medium Latest 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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Mistral Medium Latest request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
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.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. mistral/mistral-medium-3.5. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Mistral Medium Latest supports up to 256,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 262K-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.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route 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.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', 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.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'mistral/mistral-medium-3.5', 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 |
|---|
| 524K | 1.1 s | 75 tps | $0.68/M | $2.09/M | Read$0.07/M | — | +1 | | 10/06/2026 | |||||
| 262K | 1.5 s | 77 tps | $0.50/M | $1.50/M | Read$0.05/M | — | | 12/02/2025 | ||||||
| 262K | 0.4 s | 89 tps | $0.20/M | $0.20/M | Read$0.02/M | — | +1 | | 12/02/2025 | |||||
| 262K | 0.3 s | 91 tps | $0.15/M | $0.15/M | Read$0.02/M | — | | 10/16/2024 | ||||||
| 262K | 0.5 s | 190 tps | $0.15/M | $0.60/M | Read$0.02/M | — | | 09/17/2024 | ||||||
| — | $0.10/M | — | | 12/11/2023 |
Copy link to headingAbout Mistral Medium Latest
Announced April 29, 2026, Mistral Medium Latest is Mistral's first flagship merged model. Earlier lineups split the work across three families: Medium for instruction following, Magistral for reasoning, and Devstral for agentic coding. Mistral Medium Latest folds all three into a single dense 128B model and succeeds Mistral Medium 3.1 as Mistral's flagship mid-size tier.
Mistral Medium Latest scores 77.6% on SWE-Bench Verified and 91.4 on the τ³-Telecom agentic benchmark, per Mistral's announcement. The SWE-Bench result puts Mistral Medium Latest ahead of Mistral's earlier Devstral coding models.
Reasoning effort is configurable per request. Ask for a fast reply on simple prompts, or allocate more test-time compute for long agentic runs. The vision encoder handles variable image sizes and aspect ratios, so Mistral Medium Latest reads screenshots, documents, and diagrams alongside text. Native function calling and structured output support long-horizon tool use.
The weights are open under a modified MIT license. Through AI Gateway, you access Mistral Medium Latest without separate Mistral API credentials, with unified billing plus cost and latency visibility across every request.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Mistral Medium Latest merges what used to be three separate Mistral model lines. Instruction following, reasoning, and agentic coding now share one set of weights, and reasoning effort is configurable per request. Turn reasoning up for hard agentic runs and down for quick replies.
- Configuration: Reasoning spends extra output tokens on test-time compute, so budget for higher output usage when you enable it. AI Gateway's built-in observability shows the cost and latency impact per request. For simple high-volume tasks that never need reasoning or vision, a smaller model like Ministral or Mistral Small may be a better fit.
- 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 Latest
Best for
- Agentic Tool-Calling Workflows: Long-horizon runs that mix planning, reliable tool calls, and structured output
- Software Engineering Agents: Multi-file coding tasks backed by 77.6% on SWE-Bench Verified
- Multimodal Document Understanding: Tasks that combine screenshots, diagrams, or documents with text
- Model Consolidation: Replacing separate chat, reasoning, and coding models with one endpoint
- Configurable Reasoning Effort: Dialing test-time compute up or down per request
Consider alternatives when
- Largest General-Purpose Capability: You want Mistral's biggest model (consider Mistral Large 3)
- Paramount Cost Efficiency: Simple high-volume tasks don't need reasoning or vision (consider Ministral or Mistral Small)
- Fill-in-the-Middle Completion: You need a dedicated IDE completion model (consider Codestral)
Copy link to headingConclusion
Mistral Medium Latest folds Mistral's chat, reasoning, and coding lines into one model. You get configurable reasoning, image understanding, and strong agentic coding scores behind a single endpoint. Access Mistral Medium Latest through AI Gateway with unified billing and built-in observability.
Copy link to headingFrequently Asked Questions
What does it mean that Mistral Medium Latest is a merged model?
Mistral Medium Latest combines instruction following, reasoning, and agentic coding in a single set of weights. Earlier Mistral lineups split these capabilities across the Medium, Magistral, and Devstral families.
What is Mistral Medium Latest's score on SWE-Bench Verified?
77.6%, per Mistral's announcement. That result places Mistral Medium Latest ahead of Mistral's earlier Devstral coding models.
What is Mistral Medium Latest's context window?
262.1K tokens. That capacity holds large codebases, long documents, or extended agent histories in a single request.
Does Mistral Medium Latest support image inputs?
Yes. Mistral Medium Latest is multimodal, with a vision encoder that handles variable image sizes and aspect ratios across screenshots, documents, and diagrams.
Can I control how much Mistral Medium Latest reasons?
Yes. Reasoning effort is configurable per request, so you can request quick replies for simple prompts and deeper test-time compute for hard agentic runs.
What is the pricing for Mistral Medium Latest?
Check the pricing panel on this page for current rates. AI Gateway tracks pricing across every provider that serves Mistral Medium Latest.
Does AI Gateway offer Zero Data Retention for Mistral Medium Latest?
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 do I access Mistral Medium Latest?
Use Mistral Medium Latest through AI Gateway via the AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. No separate Mistral API key is required.