Mistral AI API
Mistral AI provides an API described in its client documentation for chat completion and embeddings.
- Verified facts
- 7
- Offers
- —
- Sources
- 5
- Pricing
- Metered usage
Overview
API and client scope
Mistral AI’s Python client documentation describes chat-completion and embedding APIs and says the client requires an API key. The SDK also documents synchronous and asynchronous examples. These are supplier-maintained descriptions; this review did not create an account, make a request or run a model.
The SDK lists global, EU and US server names. A server name alone does not establish data residency, processing location or availability for a particular account. Verify the contract, endpoint and data controls for the workload.
Read the full editorial overview
Costs and integration
The Python client documentation does not establish current input or output token prices, model availability, quotas, retention, training use or a service-level agreement. Mistral's pricing page, read on 9 November 2026, says most models are priced per million tokens with input and output counted separately, and that OCR, speech and tool APIs use other units; its administration documentation says creating API keys and using the API require billing activation and pay-as-you-go. The Commercial Terms of Service say Mistral AI will not use Customer Data or Outputs to train its models except in listed cases. Per-model token rates, quotas, retention and a service-level agreement are not recorded here. Compare the exact model and billing unit, and check retry and timeout behavior in the client you intend to deploy.
The Python SDK’s Apache 2.0 licence applies to the client material; it does not make the hosted API or model usage free or grant a licence to unrelated services. No benchmark, security review or paid AI call was performed.
Sources
Mistral AI API: mistral-readme · Evidence: documentation · Not checked
Documented facts
Each fact comes from official documentation and shows when it was verified.
Who it is for
Mistral AI provides an API described in its client documentation for chat completion and embeddings.
Supplier-maintained SDK documentation captured 3 November 2026. SDK description, not a service price, model guarantee or benchmark. No API request or account was created.
Coverage limits
The documented Python client requires a Mistral API key.
A credential requirement only; this does not establish account eligibility, price, billing, quota or data retention.
API interfaces
The documented API includes chat completion and embeddings interfaces.
Project SDK summary; exact models, regions and endpoint entitlements must be checked. No API request was made.
Model catalogue
Mistral Large 4, OCR 4.1, Z.ai GLM 5.3, Z.ai GLM 5.3 Flash, DeepSeek V4.1 Flash 1017, Mistral Small 4
Featured models on the supplier Models Overview page captured 9 November 2026; the page lists further models, versions and licences. Z.ai GLM and DeepSeek are described as third-party models. Account and regional access were not verified.
Billing basis
Most models are billed per million input and output tokens, with batch and cached-input discounts; OCR, speech and tool APIs use other units.
Supplier pricing-page FAQ captured 9 November 2026. The quoted example rate belongs to one model and is not repeated here; per-model rates, taxes and account eligibility need a model-specific check. Supplier statement, not a hands-on test; no account or API request.
Data controls
Under the commercial terms Mistral AI does not train its models on Customer Data or Outputs except in listed cases: products with opt-in or opt-out training settings, feedback, Order Form provisions and Labs or Preview Models.
Mistral Commercial Terms of Service captured 9 November 2026. Applies to commercial customers; consumer plans and individual products carry their own settings. Supplier terms, not legal advice; no account created.
Availability
API keys and API use require billing activation with pay-as-you-go; the Free mode covers Vibe and Studio but not the API.
Supplier Admin documentation (Usage and limits) captured 9 November 2026. Plan terms and included usage can change; no account was created and no API request made.
Not confirmed in our sources
We have not confirmed these terms for Mistral AI API in the linked documentation. That does not mean Mistral AI API lacks them; confirm them before you rely on them.
- Pricing
Sources & methodology
Facts come from the linked documentation. Documentation checks are not hands-on tests, and readable sources can have incomplete coverage.
Discovered an undocumented discrepancy or pricing shift? Submit a correction request.
Submit correctionMistral AI API alternatives
Other AI providers tools to weigh. Different billing units do not establish a cost winner, so compare plans side by side.
OpenAI API
AI providers
Hosted models for text and image inputs, with Responses API access and client SDKs. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Anthropic Claude API
AI providers
Programmatic access to Claude models through a REST API. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Google Gemini API
AI providers
A developer API catalogue with text, multimodal, audio and image model families. · Evidence needs recheck
PricingUsage-basedPrice needs recheckPrice terms
Usage-based API pricing
Mistral AI API comparisons
Compare two products in the same category using their documented terms and sources.
- Mistral AI API vs Anthropic Claude API
- Mistral AI API vs DeepInfra
- Mistral AI API vs Google Gemini API
- Mistral AI API vs Nebius Token Factory
- Mistral AI API vs OpenAI API
- Mistral AI API vs Perplexity API Platform
- Mistral AI API vs Replicate
- Mistral AI API vs Together AI
- Mistral AI API vs xAI API
- Mistral AI API vs Baseten
- Mistral AI API vs Cerebras Inference
- Mistral AI API vs Cohere API
- Mistral AI API vs Fireworks AI API
- Mistral AI API vs Groq API
- Mistral AI API vs Hugging Face Inference Providers
- Mistral AI API vs IBM watsonx.ai
- Mistral AI API vs NVIDIA NIM
- Mistral AI API vs OpenRouter API
- Mistral AI API vs SambaCloud