Mistral Small 4 (Reasoning)

by Mistral AI

Mistral Small 4 (Reasoning) is a reasoning model from Mistral AI, released on March 16, 2026. It has a 256K-token context window and can generate up to 256K output tokens. API pricing is $0.15 per 1M input tokens and $0.6 per 1M output tokens. It ranks #130 of 220 models by Intelligence Score with a score of 18.9.

Mistral Small 4 is Mistral AI's hybrid small model that unifies instruct, reasoning, multimodal understanding, and coding capabilities in a single efficient system. It uses a 119B-parameter Mixture-of-Experts architecture with native image input, a 256k context window, and configurable reasoning depth for general chat, coding agents, and long-context reasoning workloads.

Key specs

ProviderMistral AI
Release date2026-03-16
Licenseopen source
Context window256K tokens
Max output256K tokens
Input price$0.15 / 1M tokens
Output price$0.6 / 1M tokens
Intelligence Score18.9
Coding index10.6
Output speed328 tokens/s
Time to first token1.53 s

Quick answers

What is the context window of Mistral Small 4 (Reasoning)?

Mistral Small 4 (Reasoning) has a context window of 256K tokens, with a maximum output of 256K tokens per response.

How much does Mistral Small 4 (Reasoning) cost?

Mistral Small 4 (Reasoning) costs $0.15 per 1M input tokens and $0.6 per 1M output tokens through the API.

Is Mistral Small 4 (Reasoning) open source?

Yes. Mistral Small 4 (Reasoning) is an open model released under the open source license.

When was Mistral Small 4 (Reasoning) released?

Mistral AI released Mistral Small 4 (Reasoning) on March 16, 2026.

How does Mistral Small 4 (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

Mistral Small 4 (Reasoning) scores 18.9 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.15 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Mistral AI