Mistral Small 3.2 24B
Pick up to 3 models · pricing, context and capabilities · simulate your product cost
Data updated on September 30, 2026· 217 models
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.
- Reasoning estimated
- Speed estimated
- Input
- Output
- Context
- 256 K tokens
- Max output
- 16 K
- Input, $ per 1M tokens
- $0.094
- Output, $ per 1M tokens
- $0.250
- Cache read, $ per 1M
- —
- Batch (input / output)
- —
- Tool calling
- Yes
- Released
- 06/20/2025
- Knowledge cutoff
- —
- API id
- mistralai/mistral-small-3.2-24b-instruct
Summary from the data
Mistral Small 3.2 24B is a Mistral model available by API since 06/20/2025. It costs $0.094 per million input tokens and $0.250 per million output tokens, accepts 256 K tokens of context and generates up to 16 K tokens per response. Input: image, text; output: text. It has no reasoning mode. It supports tool calling. With 10,000 requests a month of 1,500 input and 400 output tokens it would cost about $2.41 a month.
Compare Mistral Small 3.2 24B with…
- Mistral Small 3.2 24B vs Mistral Medium 3.5
- Mistral Small 3.2 24B vs Mistral Small 4
- Mistral Small 3.2 24B vs Mistral Large 3 2512
- Mistral Small 3.2 24B vs Claude Sonnet 5.5
- Mistral Small 3.2 24B vs DeepSeek V4.1 Flash
- Mistral Small 3.2 24B vs Gemini 3.8 Flash
- Mistral Small 3.2 24B vs Kimi K3
- Mistral Small 3.2 24B vs GPT-6.1 Sol
- Mistral Small 3.2 24B vs Qwen3.8 Max Prime
- Mistral Small 3.2 24B vs Grok 4.7
What would your product cost?
Estimate the monthly cost with your app's real volume. List prices, no cache or batch discounts.
The 6 cheapest for this scenario (chat, last 12 months)
- 1Lyria 3 Pro Preview Google$0.00
- 2Lyria 3 Clip Preview Google$0.00
- 3Qwen3.7 Flash Qwen$0.97
- 4DeepSeek V4 Flash 0731 DeepSeek$1.55
- 5Ministral 3 3B 2512 Mistral$1.90
- 6Qwen3.5-Flash Qwen$2.02
Frequently asked questions
How much does Mistral Small 3.2 24B cost per million tokens?
Mistral Small 3.2 24B costs $0.094 per million input tokens and $0.250 per million output tokens (USD, list price). Cache read: not published. Batch tier: not published.
What context window does Mistral Small 3.2 24B have?
Mistral Small 3.2 24B accepts 256 K tokens of context per request and generates up to 16 K tokens per response.
Does Mistral Small 3.2 24B accept images, audio or files?
Input: image, text. Output: text.
Does Mistral Small 3.2 24B have a reasoning mode and tool calling?
It has no reasoning mode. It supports tool calling.
When was Mistral Small 3.2 24B released and what is its knowledge cutoff?
Mistral Small 3.2 24B has been available by API since 06/20/2025. Knowledge cutoff: not published.
What would an app built on Mistral Small 3.2 24B cost?
With 10,000 requests a month of 1,500 input and 400 output tokens, Mistral Small 3.2 24B would cost about $2.41 a month at list price, without cache or batch discounts.
What is the API id of Mistral Small 3.2 24B?
The id is mistralai/mistral-small-3.2-24b-instruct. It is the name passed in the model parameter of the API (or on OpenRouter).
Where do the prices come from and how often are they updated?
From the public catalogs of OpenRouter, models.dev and LiteLLM, which publish each provider's list prices. They sync once a day and the last update date is shown above the comparison.
What does price per million tokens mean?
It is what the provider charges per million tokens you send (input) or the model generates (output). A token is roughly 4 characters. Output almost always costs more than input.
Sources: OpenRouter, models.dev and LiteLLM. Prices in USD per million tokens, list price, no volume discounts. Prompt tokens are an estimate; each provider's tokenizer may differ.