token.appMistral AI › Mistral Small 3.2 24B

Mistral Small 3.2 24B pricing & benchmarks

Mistral Small 3.2 24B is available from Mistral AI at $0.094 per million input tokens and $0.250 per million output tokens ($0.133 blended at 3:1). It accepts up to 256,000 tokens of context. Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compared to the 3.1 release, version 3.2 significantly improves acc…

Pricing
Per million tokens · OpenRouter
Input$0.094
Output$0.250
Blended (3:1)$0.133
Specification
mistralai/mistral-small-3.2-24b-instruct
Context window256K
Max output16K
ReleasedJun 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for Mistral Small 3.2 24B yet. We show nothing rather than reprinting an unverified figure.
Where to run Mistral Small 3.2 24B
3 hosts · 1.3× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
HostBlended $/1MIn / OutContextWeightsUptime 24h
DeepInfra
⚠ 128K context, not 256K
$0.106 $0.075 / $0.200 128K fp8 98.8%
Venice $0.133 $0.094 / $0.250 256K fp8 98.5%
Parasail
⚠ 131K context, not 256K
$0.143 $0.090 / $0.300 131K bf16 98.9%
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Mistral Small 3.2 24B
FAQ
How much does Mistral Small 3.2 24B cost?
Mistral Small 3.2 24B costs $0.094 per million input tokens and $0.250 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.133 per million tokens.
What is Mistral Small 3.2 24B's context window?
Mistral Small 3.2 24B accepts up to 256,000 tokens of context, and can generate up to 16,384 output tokens.