---
id: "mistralai/mistral-small-3.2-24b-instruct"
also: ["mistralai/mistral-small-3.2-24b-instruct-2506", "mistralai/Mistral-Small-3.2-24B-Instruct-2506"]
card_usd_per_m: "0.1 in, 0.3 out, at mistral/eu"
cheapest_list_usd_per_m: "0.075 in, 0.2 out, at deepinfra/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.0705 in, 0.2964 out, at mistral/eu on openrouter"
context: 256000
max_output: 26214
input: ["image", "text"]
output: ["text"]
released: "2025-06-20"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 4
gateways: "openrouter (4)"
no_training: 4
trains: 0
retains_prompts: 0
---
# Mistral: Mistral Small 3.2 24B

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 accuracy on...