How much does Mistral: Mistral Small 3.2 24B Instruct 2506 cost?

Mistral: Mistral Small 3.2 24B Instruct 2506 costs $0.07 per 1M input tokens and $0.20 per 1M output tokens.

What is the context length of Mistral: Mistral Small 3.2 24B Instruct 2506?

Mistral: Mistral Small 3.2 24B Instruct 2506 has a 128,000 token context window.

Does Mistral: Mistral Small 3.2 24B Instruct 2506 support tool calling and structured outputs?

Yes. Mistral: Mistral Small 3.2 24B Instruct 2506 supports tool calling and structured outputs.

What inputs and outputs does Mistral: Mistral Small 3.2 24B Instruct 2506 support?

Mistral: Mistral Small 3.2 24B Instruct 2506 accepts text and image as input and returns text.

When was Mistral: Mistral Small 3.2 24B Instruct 2506 released?

Mistral: Mistral Small 3.2 24B Instruct 2506 was released on Jun 20, 2025.

Mistral Small 3.2 24B Instruct 2506

MistralReleased Jun 20, 2025mistralai/mistral-small-3.2-24b-instruct-2506

Cost Compare

Mistral Small 3.2 is a drop-in upgrade over 3.1 with better instruction following, fewer infinite-generation errors and a more robust function-calling interface.

Context

128K

Max output

128K

Input /1M

$0.07

Output /1M

$0.20

Blended /1M

$0.11

AcceptsTextImageProducesTextTokenizer Mistral

Providers

FastRouter routes your requests to this provider. You can also bring your own key.

Pricing tier

ProviderInput /1MOutput /1MContextMax outputLatencyThroughput

DeepInfrafp8

deepinfra

Input /1M$0.07

Output /1M$0.20

Context128K

Max output128K

Latency—

Throughput—

Supported parameters

Request parameters you can send with this model.

Core (Sampling & basic generation)

max_tokens: Maximum tokens to generate.
min_p: Minimum probability threshold for sampling.
seed: Seed for deterministic sampling.
stop: Sequences where generation stops.
temperature: Controls randomness of output.
top_k: Limits sampling to top K tokens.
top_p: Nucleus sampling threshold.

Penalties (Token Penalties)

frequency_penalty: Penalizes frequent tokens.
presence_penalty: Penalizes tokens already present.
repetition_penalty: Penalizes repeated tokens.

Tool Use (Function Calls & Tools)

tool_choice: How the model should use tools.
tools: Tool/function definitions available to the model.

Output & Format (Response Formatting)

logprobs: Return log probabilities of output tokens.
response_format: Structured output format configuration.
structured_outputs: Enforce a structured output schema.

Performance

Median throughput and time to first token per provider over the last week.

Throughput

Latency

Make your first API call

OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.

Full API docs

Replace <FASTROUTER_API_KEY> with your key · Get your key →Install

OpenAI SDKHTTP

from openai import OpenAI

client = OpenAI(

base_url="https://api.fastrouter.ai/api/v1", # FastRouter base URL

api_key= "<FASTROUTER_API_KEY>", # Replace with your FastRouter API key

)

completion = client.chat.completions.create(

model="mistralai/mistral-small-3.2-24b-instruct-2506", # Replace with your model ID

messages=[

{ "role": "user", "content": "What is the meaning of life?" }

]

)

print(completion.choices[0].message.content)

Frequently asked questions

Model scores sourced from ArtificialAnalysis