Mistral AI website screenshot

Mistral AI

Mistral AI provides state-of-the-art large language models and AI APIs for developers and enterprises.

Mistral AI publishes 11 APIs on the APIs.io network, including Chat API, Mistral Embeddings API, Mistral Moderation API, and 8 more.

The Mistral AI catalog on APIs.io includes 1 event-driven AsyncAPI specification, 1 JSON-LD context, and 2 Spectral governance rulesets.

Mistral AI’s developer surface includes authentication, documentation, getting-started guide, pricing, GitHub presence, developer portal, engineering blog, and 22 more developer resources.

63.2/100 strong ▬ flat Agent 54/100 agent ready Full breakdown ↓
scored 2026-07-21 · rubric v0.4
11 APIs 16 Features

API Rating

API Evangelist API Evangelist Rating How this is scored →
scored 2026-07-21 · rubric v0.4
Composite quality — 63.2/100 · strong
Contract Quality 20.0 / 25
Developer Ergonomics 9.6 / 20
Commercial Clarity 14.2 / 20
Operational Transparency 8.9 / 13
Governance 6.3 / 12
Discoverability 4.3 / 10
Agent readiness — 54/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 15 / 15
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 6 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/mistral: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs

Mistral AI Chat API

Chat completion API for conversational AI using Mistral's language models.

Mistral Embeddings API

Generate vector embeddings for text and code using Mistral's embedding models for retrieval, clustering, classification, and semantic search.

Mistral Moderation API

Content moderation and classification API for detecting potentially harmful or inappropriate content across nine safety categories including text and chat moderation.

Mistral AI Agents API

Agent completions API for building AI agents that can handle complex tasks, maintain context, coordinate multiple actions, and use tools including function calling.

Mistral AI FIM API

Fill-in-the-Middle code completion API powered by Codestral for generating code between a given prompt and suffix, supporting over 80 programming languages.

Mistral AI OCR API

Optical Character Recognition API that extracts text, images, tables, and structured data from documents and PDFs with support for complex layouts, LaTeX, and mathematical expre...

Mistral AI Fine-Tuning API

Fine-tuning API for customizing Mistral models on your own datasets, supporting text, vision, and classifier fine-tuning with configurable hyperparameters and integrations.

Mistral AI Files API

File management API for uploading, retrieving, downloading, and deleting files used across fine-tuning, batch processing, and OCR endpoints with support for files up to 512 MB.

Mistral AI Models API

Models management API for listing available models, retrieving model details, and managing fine-tuned models including archiving and updating.

Mistral AI Batch API

Batch inference API for processing up to one million requests asynchronously at reduced cost, supporting chat completions, embeddings, FIM, moderations, OCR, classifications, an...

Mistral AI Audio Transcription API

Audio transcription API powered by Voxtral for converting speech to text with support for speaker diarization, word-level timestamps, context biasing, and real-time streaming ac...

Collections

GraphQL

Mistral AI GraphQL Schema

Conceptual GraphQL schema for the Mistral AI API. Mistral AI exposes a REST API (OpenAI-compatible) at `https://api.mistral.ai/v1`. This schema translates those REST resources i...

GRAPHQL

Pricing Plans

Mistral Plans Pricing

6 plans

PLANS

Scroll for all 11

Rate Limits

Mistral Rate Limits

4 limits

RATE LIMITS

FinOps

Features

Mistral Large 2 at $2/$6 per MTok
Mistral Medium 3 at $0.40/$2
Mistral Small 3 at $0.10/$0.30
Ministral 3B at $0.04/$0.04 (smallest commercial model)
Mistral Nemo at $0.02/$0.04 (cheapest tier)
Codestral at $0.30/$0.90 for code completion/FIM
Pixtral Large for vision
Mixtral 8x22B mixture-of-experts
La Plateforme free tier with 1 RPS
Paid tier: 10 RPS, 5M TPM
OpenAI-compatible Chat Completions
Function calling and tool use
JSON mode and guided generation
Embed model for semantic search
Available on AWS Bedrock, Azure AI, Vertex AI
Fine-tuning service for select models

Event Specifications

Mistral AI Streaming Completions API

AsyncAPI definition for Mistral AI streaming completion endpoints. Mistral is OpenAI-compatible and delivers streamed completions as Server-Sent Events (SSE) over HTTP when `str...

ASYNCAPI

Semantic Vocabularies

Mistral Context

0 classes · 11 properties

JSON-LD

API Governance Rules

Mistral AI API Rules

9 rules · 1 errors 8 warnings

SPECTRAL

Mistral AI API Rules

6 rules · 5 warnings 1 info

SPECTRAL

JSON Structure

Mistral Structure

0 properties

JSON STRUCTURE

Resources

Get Started 4

Portal, sign-up, and the first successful call

Documentation 5

Reference material describing how the API behaves

Agent Surfaces 2

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 1

Pagination, idempotency, versioning, errors, and events

Build 4

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 3

Status, limits, changes, and where to get help

Commercial 4

Pricing, plans, and the legal terms of use

Company 4

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
opencollection: 1.0.0
info:
  name: Mistral AI OCR API
  version: '1.0'
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: OCR
    type: folder
  items:
  - info:
      name: Mistral AI Process a document with OCR
      type: http
    http:
      method: POST
      url: https://api.mistral.ai/v1/ocr
      body:
        type: json
        data: '{}'
    docs: Extract text, images, tables, and structured data from documents, PDFs, or images. Returns structured Markdown with
      extracted content including mathematical expressions in LaTeX format.
bundled: true