Mistral AIMistral SmallTool use

Mistral Small 3 pricing

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llama 3.3 70B and Qwen 32B, while operating at three times the speed on equivalent hardware. [Read the blog post about the model here.](https:. Live index: 4 priced offers. Best input $0.050 per million tokens from Openrouter. Best output $0.080 per million tokens from Openrouter.

33K context·4 providers·verified Apr 7, 2026
Best input$0.050per 1M tokens · Openrouter
Best output$0.080per 1M tokens · Openrouter

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 4 offers are listed for Mistral Small 3. Best input in this view: Openrouter.

O
Openrouter
Input / 1M
$0.050
Output / 1M
$0.080
FA
Fireworks AI
Input / 1M
$0.900
Output / 1M
$0.900
TA
Together AI
Input / 1M
N/A
Output / 1M
N/A
D
DeepInfra
Input / 1M
$0.050
Output / 1M
$0.080

Input vs output · per provider

Cost calculator

Pick any of the providers above and type how many tokens you expect per day, week, or year. We turn that into rough dollar totals for Mistral Small 3.

Provider

In: $0.050/M·Out: $0.080/M

0.005000¢ / req

0.004000¢ / req

Daily
$0.90
Monthly
$27
Annual
$329

Model specifications

Context length, caps, and capability flags for Mistral Small 3. Family: Mistral Small. Values follow the main provider (Mistral AI) record in our index.

Context window
32,768 tokens
Max output
32,768 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Jan 2025
Primary provider
Mistral AI
Model family
Mistral Small

Compare Mistral Small 3

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for Mistral Small 3.

Frequently asked questions

Read these after the table if you want plain language around Mistral Small 3 rates. The short model note from our index: Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed ...

Yes. Mistral Small 3 is available on Openrouter, Fireworks AI, Together AI, DeepInfra.

Also from Mistral AI

Other models by Mistral AI with live pricing in our catalog.