Mistral Small 3.1 24B vs Mistral Small 3.2 24B

Compare Mistral Small 3.1 24B from Mistral AI and Mistral Small 3.2 24B from Mistral AI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Mistral Small 3.1 24B vs Mistral Small 3.2 24B: side-by-side summary

Mistral Small 3.1 24B and Mistral Small 3.2 24B are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Mistral Small 3.1 24B, from Mistral AI, has a 128,000-token context window and is priced at $0.351/M tokens input, $0.555/M tokens output on OpenRouter.

Mistral Small 3.2 24B, from Mistral AI, has a 256,000-token context window and is priced at $0.075/M tokens input, $0.20/M tokens output on OpenRouter.

Context window

Mistral Small 3.1 24B: 128,000 tokens
Mistral Small 3.2 24B: 256,000 tokens

Price

Mistral Small 3.1 24B: $0.351/M tokens input, $0.555/M tokens output
Mistral Small 3.2 24B: $0.075/M tokens input, $0.20/M tokens output

Provided by

Mistral Small 3.1 24B: Mistral AI
Mistral Small 3.2 24B: Mistral AI

Mistral Small 3.1 24B vs Mistral Small 3.2 24B at a glance

Mistral Small 3.1 24B vs Mistral Small 3.2 24B comparison
Attribute	Mistral Small 3.1 24B	Mistral Small 3.2 24B
Input price	$0.351/M tokens	$0.075/M tokens
Output price	$0.555/M tokens	$0.20/M tokens
Context window	128,000 tokens	256,000 tokens
Intelligence Index	Not available	Not available
Coding Index	Not available	Not available
Agentic Index	Not available	Not available
Latency (p50)	0.77 s	0.69 s
Throughput (p50)	31.0 tok/s	33.0 tok/s

Frequently asked questions

Is Mistral Small 3.1 24B cheaper than Mistral Small 3.2 24B?

Mistral Small 3.2 24B is cheaper than Mistral Small 3.1 24B on OpenRouter: Mistral Small 3.2 24B costs $0.075/M tokens input and $0.20/M tokens output, while Mistral Small 3.1 24B costs $0.351/M tokens input and $0.555/M tokens output.

Which has the longer context window, Mistral Small 3.1 24B or Mistral Small 3.2 24B?

Mistral Small 3.2 24B has the longer context window at 256,000 tokens, compared with 128,000 tokens for Mistral Small 3.1 24B.

Which is faster, Mistral Small 3.1 24B or Mistral Small 3.2 24B?

Mistral Small 3.2 24B is faster on OpenRouter, generating a median 33.0 tokens per second compared with 31.0 tokens per second for Mistral Small 3.1 24B.

Mistral Small 3.1 24B vs Mistral Small 3.2 24B

Mistral Small 3.1 24B vs Mistral Small 3.2 24B

Overview