# Mistral AI

**Canonical:** https://apis.io/providers/mistralai/  
**Website:** https://mistral.ai  
**APIs profiled:** 11

Mistral AI is a Paris-based artificial intelligence company that develops and operates frontier open-weight and commercial large language models, exposed to developers and enterprises through La Plateforme (api.mistral.ai). The developer platform provides an OpenAI-compatible REST surface spanning chat completions, embeddings, content moderation, agents and tool-use, fill-in-the-middle code completion (Codestral), document OCR, audio transcription (Voxtral), fine-tuning, file management, model management, and asynchronous batch inference. Access is via a bearer API key issued from the console, with first-party Python and TypeScript SDKs, published pricing, a status page, and a dated changelog.

## Kin Score — 33.5 / 100 (thin)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 33.5).

| Facet | Score |
|---|---|
| Discoverability | 81.5 |
| Contract Quality | 0.0 |
| Governance | 4.5 |
| Contract Governance | 4.5 |
| Operational Transparency | 42.1 |
| Developer Ergonomics | 69.0 |
| Commercial Clarity | 27.6 |
| Access Clarity | 27.6 |

## Agent readiness — 8.5 (agent-aware)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | yes |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Self-serve signup — onboarding: self-serve, pricing: unknown, trial: no (confidence: medium).

## APIs (11)

- **Mistral AI Chat API** — Chat completion API for conversational AI using Mistral's language models, with function calling, streaming, and JSON / structured output.
- **Mistral Embeddings API** — Generate vector embeddings for text and code for retrieval, clustering, classification, and semantic search.
- **Mistral Moderation API** — Content moderation and classification API for detecting harmful content across nine safety categories for text and chat.
- **Mistral AI Agents API** — Agent completions API for building AI agents that handle complex tasks, maintain context, coordinate actions, and use tools and connectors.
- **Mistral AI FIM API** — Fill-in-the-Middle code completion API powered by Codestral for generating code between a prompt and suffix across 80+ languages.
- **Mistral AI OCR API** — Document AI / OCR API that extracts text, images, tables, and structured data from documents and PDFs with complex layouts.
- **Mistral AI Fine-Tuning API** — Fine-tuning API for customizing Mistral models on your own datasets, supporting text, vision, and classifier fine-tuning.
- **Mistral AI Files API** — File management API for uploading, retrieving, downloading, and deleting files used across fine-tuning, batch, and OCR.
- **Mistral AI Models API** — Models management API for listing available models, retrieving model details, and managing fine-tuned models.
- **Mistral AI Batch API** — Batch inference API for processing up to one million requests asynchronously at reduced cost across most endpoints.
- **Mistral AI Audio Transcription API** — Audio transcription API powered by Voxtral for speech-to-text with diarization, word-level timestamps, and streaming.

## Security (2)

- **Mistralai Authentication** — apiKey · 1 scheme
- **Mistralai Domain Security** — TLSv1.3 · HSTS · DMARC

## Tags

Company, Artificial Intelligence, Large Language Models, Generative AI, Machine-Learning, Chat, Embeddings, Agents, OCR, Fine-Tuning, Developer Platform

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/mistralai/). Scores are computed from the provider's own public artifacts under a published rubric.