Mistral: Mistral Small 3.2 24B

2 providers live

mistralai/mistral-small-3.2-24b-instruct

→

2 live providers
100% uptime
0.19 s first token
134 tok/s output
25% off

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.

Context: 128K; tokens
Max output: 32K; tokens
Input: ~~$0.1729~~ $0.129675; per million tokens, 25% off
Output: ~~$0.4034~~ $0.30255; per million tokens, 25% off

Providers

Ranked by price and speed. Requests go to the best healthy provider, then fail over down the list.Benchmarks

Live providers of Mistral Small 3.2 24B, in the router's order
Who answers now	Input per 1M	First token
llm.buzz25% offpicked	~~$0.1729~~ $0.129675	2.07 s
ScalewayEU	$0.1729	0.19 s

llm.buzz answers now: lowest price.

First token is the 24-hour median. If the pick fails, the next one answers at its own price.

#	Provider	Input	Output	Cache read	Latency	Throughput	Uptime (3d)
1	llm.buzzAuto25% offNon-EU Data policy not declared	~~$0.1729~~ $0.129675	~~$0.4034~~ $0.30255	n/a	2.07 s	134 tok/s	80.3%
2	ScalewayEU Data policy not declared	$0.1729	$0.4034	n/a	0.19 s	93 tok/s	100%

Want to serve this model?Become a provider

Price history

Input price since Oct 21, 2026, in USD per million tokens. The history shows prices before discounts.

Data table

Provider	From	Input	Output
Scaleway	Oct 21, 2026	$0.1733	$0.4044
Scaleway	Oct 22, 2026	$0.1736	$0.405
Scaleway	Oct 22, 2026	$0.1732	$0.404
Scaleway	Oct 23, 2026	$0.173	$0.4036
Scaleway	Oct 26, 2026	$0.1729	$0.4034

Performance

Last 24 hours, from llm.buzz's test requests

Throughput (tok/s)

llm.buzz134 tok/s
Scaleway93 tok/s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 07:00	134 tok/s	134 tok/s	134 tok/s
llm.buzz	Oct 27, 00:00	93 tok/s	93 tok/s	93 tok/s
llm.buzz	Last 24 hours	134 tok/s	93 tok/s	93 tok/s
Scaleway	Oct 26, 08:00	78 tok/s	78 tok/s	78 tok/s
Scaleway	Oct 26, 13:00	54 tok/s	54 tok/s	54 tok/s
Scaleway	Oct 26, 17:00	93 tok/s	93 tok/s	93 tok/s
Scaleway	Oct 26, 23:00	161 tok/s	161 tok/s	161 tok/s
Scaleway	Oct 27, 03:00	134 tok/s	134 tok/s	134 tok/s
Scaleway	Last 24 hours	93 tok/s	54 tok/s	54 tok/s

Latency (time to first token)

llm.buzz2.07 s
Scaleway0.19 s

Data table

Provider	From (UTC)	p50	p90	p99
llm.buzz	Oct 26, 07:00	2.07 s	2.07 s	2.07 s
llm.buzz	Oct 27, 00:00	2.07 s	2.07 s	2.07 s
llm.buzz	Last 24 hours	2.07 s	2.07 s	2.07 s
Scaleway	Oct 26, 08:00	0.23 s	0.23 s	0.23 s
Scaleway	Oct 26, 13:00	0.19 s	0.19 s	0.19 s
Scaleway	Oct 26, 17:00	0.19 s	0.19 s	0.19 s
Scaleway	Oct 26, 23:00	0.19 s	0.19 s	0.19 s
Scaleway	Oct 27, 03:00	0.23 s	0.23 s	0.23 s
Scaleway	Last 24 hours	0.19 s	0.23 s	0.23 s

Uptime

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

Scaleway

Up: 95% or more served
Degraded: 85% to 95%
Down: below 85%
No data
From llm.buzz's test requests

Questions

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

Mistral: Mistral Small 3.2 24B costs $0.129675 per million input tokens and $0.30255 per million output tokens at llm.buzz, the provider requests go to first. These prices are 25% off until 2026-11-06 00:00 UTC. Each provider sets its own price, and you pay the price of the provider that answered.

Do providers train on my prompts?

Each provider declares it, and the table above shows every declaration. You can limit a request to providers that keep nothing, or to providers in the EU.

Can I serve Mistral: Mistral Small 3.2 24B myself?

Yes. Apply as a provider, add your endpoint and list this model at your price. It goes live once the automated check passes.

Similar models

OpenAI: GPT-4o-miniopenai/gpt-4o-mini

128K context, $0.15 input and $0.60 output. 2 providers.

Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash

1M context, $0.15 input and $0.47 output. 1 provider.

Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5

1M context, $0.10 input and $0.50 output. 2 providers.

Call it

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llm.buzz/api/v1",
    api_key=os.environ["LLM_BUZZ_KEY"],
)
reply = client.chat.completions.create(
    model="mistralai/mistral-small-3.2-24b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llm.buzz/api/v1",
  apiKey: process.env.LLM_BUZZ_KEY,
});
const reply = await client.chat.completions.create({
  model: "mistralai/mistral-small-3.2-24b-instruct",
  messages: [{ role: "user", content: "Hello" }],
});

curl https://api.llm.buzz/api/v1/chat/completions \
  -H "Authorization: Bearer $LLM_BUZZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "mistralai/mistral-small-3.2-24b-instruct",
       "messages": [{"role": "user", "content": "Hello"}]}'

Endpoints

POST /api/v1/chat/completionsPOST /api/v1/responsesPOST /api/v1/messages

Authentication

Send your llm.buzz key as a Bearer token: Authorization: Bearer $LLM_BUZZ_KEY. Create keys in the console. The same key calls every model; each request pays the price of the provider that answered it.

More in Authentication and the API reference.

Call Mistral: Mistral Small 3.2 24B with one keyEach request pays the price of the provider that answered it.

Get API key

Mistral: Mistral Small 3.2 24B

Providers

Price history

Performance

Throughput (tok/s)

Latency (time to first token)

Uptime

Questions

Similar models

Call it

Authentication

README