LLM Reference

Mistral Small

Released
2024-02-26
Last refreshed
2026-06-15
Status
Researched 25d ago
Open sourceCommercial use: permittedClassificationJSON / Tool use

Mistral Small is worth evaluating for classification and json / tool use when its provider route and context window match the workload.

Use it for

  • Teams evaluating classification and json / tool use
  • Workloads that can use a 32k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Vision or document-understanding workloads
Specifications
Released
2024-02-26
Context
32k
Parameters
22B
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Training
Fine-tuned
Created by

Enterprise AI solutions for trust and transparency.

Paris, France
Founded 2023
Website
Pricing
Output / 1M
$0.300
Input / 1M
$0.100

Cheapest of 5 routes · Mistral AI Studio

About

Mistral Small is a language model from MistralAI. It offers a 32K-token context window.

Mistral Small (API identifier: mistral-small-2402) is Mistral AI's first-generation Small tier model, released in February 2024 as part of a commercial API family that offered three capability tiers: Mistral Tiny, Mistral Small, and Mistral Medium. It is positioned above the open-source Mixtral 8x7B in Mistral's capability hierarchy. The model supports a 32,768-token context window, multilingual instruction following across European languages, and tool calling for structured API interactions. Specific parameter counts for this commercial tier have not been publicly disclosed by Mistral AI.

Mistral Small targets cost-efficient production deployments requiring strong instruction following, code generation, and multilingual support without the premium of the Medium or Large tiers. It supports multiple European languages and delivers reliable performance on classification, summarization, code assistance, and structured extraction tasks at lower cost per token than the higher tiers.

The model is available through Mistral AI's API, AWS Bedrock, Azure AI Foundry, Fireworks AI, and DeepInfra. Later versions—Mistral Small 2 (September 2024, 22B parameters), Mistral Small 3, 3.1, and 4—have substantially superseded this release with improved benchmarks, updated context windows, and in later variants, vision capability. The original mistral-small-2402 remains available for legacy integrations.

Mistral Small has a 32k-token context window.

Mistral Small input tokens at $0.1/1M, output at $0.3/1M.

Top use-case fit

Classification

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 5

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Mistral AI Studio$0.100$0.300
Serverless
AWS Bedrock$1.00$3.00
Serverless
Microsoft Foundry$1.00$3.00
Provisioned
DeepInfra--
ServerlessPartial

Available via routers & gateways(14)

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.