Skip to content
ArenaPlatform

Mistral Small 4

mistral/mistral-small-2603

Mistral Small 4 (March 2026), an Apache 2.0 MoE with 119B total and about 6.5B active parameters that merges instruct, reasoning (formerly Magistral) and coding (formerly Devstral), with a 256K context and per-request reasoning effort.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral/mistral-small-2603",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read docs
Input Price
$0.1275 / 1M tokens
Output Price
$0.51 / 1M tokens
Context
262.1K tokens
Output Cap
262.1K tokens

Capabilities

Explore what Mistral Small 4 supports, then use the API section for a request tailored to this model.

Max tokensReasoningInclude reasoning

Model Information

Provider
Mistral AI
Product
Language Models
Release Date
Mar 16, 2026
Data Policy
Configurable
Region
Global
Input
Text
Output
Text
Provider Documentation

Playground

Try Mistral Small 4 by Mistral AI. Requests use the selected workspace’s credits and API pricing.

Mistral Small 4Credits —
Mistral Small 4
⌘ / Ctrl + Enter to send
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for Mistral Small 4.

ProviderContextOutput CapInput PriceOutput PriceEndpoint
Mistral AI262.1K tokens262.1K tokens$0.1275 / 1M tokens$0.51 / 1M tokens
mistral-small-2603

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens262144
Max output tokens262144

Provider Notes

General LLM inference is an integration preview. Managed billing and deployment acceptance must be enabled before requests can be served.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "mistral/mistral-small-2603",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelmistral/mistral-small-2603 — Required model identifier.
max_tokensView Accepted Values
reasoningView Accepted Values
include_reasoningView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens262144
Max output tokens262144

Similar Models

Explore more language models and compare their capabilities.

ModelContextInput PriceOutput Price
Mistral Medium 3.5Mistral AI262.1K tokens$1.275 / 1M tokens$6.375 / 1M tokens
Ministral 3 3BMistral AI262.1K tokens$0.085 / 1M tokens$0.085 / 1M tokens
Ministral 3 8BMistral AI262.1K tokens$0.1275 / 1M tokens$0.1275 / 1M tokens
Ministral 3 14BMistral AI262.1K tokens$0.17 / 1M tokens$0.17 / 1M tokens
Mistral Large 3Mistral AI262.1K tokens$0.425 / 1M tokens$1.275 / 1M tokens
Codestral 25.08Mistral AI256K tokens$0.255 / 1M tokens$0.765 / 1M tokens
View All Language Models