Mistral: Mistral Small 3

Public pricingIntelligence 79/100Medium memoryUso de ferramentas

Mistral: Mistral Small 3 é um modelo texto criado para chat geral, análise e uso em produção. Ele combina baixa latência e inferência eficiente, um contexto de 33K tokens e um perfil baixo custo para entregar trabalho confiável em general chat, analysis, and production workloads.

Input

$0.05/1M

Output

$0.08/1M

Cached

$0.03/1M

Batch

$0.05/1M

Calculate your Mistral Small 3 bill.

Set your workload — see cost at your exact volume.

What would Mistral Small 3 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Mistral Small 3 at a glance.

Memory

32,768

tokens

Max reply

16,384

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

mistral

Released

Jan 2025

Training cutoff

Oct 2023

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • mmlu

    81

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Mistral Small 3

  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.

Alternatives

Similar models to compare.

FAQ

Mistral Small 3 — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Mistral Small 3 costs roughly $7 per month. Input is $0.05 /1M tokens and output is $0.08 /1M tokens.
Mistral Small 3 has a 32,768-token context window (medium memory — a long report or a codebase file). That means you can fit about 6,144 words of input and history in a single call.
Beyond text generation, Mistral Small 3 supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Mistral Small 3 was released in January 2025, with training data cut off around October 2023.
Models in a similar class include Mistral Small 3.2 24B, Mistral Nemo, Devstral Small 1.1. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Mistral Small 3 against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard