Mistral: Mistral Small 4

Public pricingIntelligence 79/100Large memory비전도구 활용

Mistral: Mistral Small 4은 멀티모달 추론과 분석에 맞춘 멀티모달 모델입니다. 멀티모달 입력 처리、깊은 추론과 계획, 262K tokens의 컨텍스트, 저비용 특성을 결합해 멀티모달 추론과 분석에서 안정적인 작업을 돕습니다. 특히 지연, 비용, 처리량가 중요한 경우에 잘 맞으며, 안정적인 출력, 유연한 배포, 확장성을 중시하는 팀에 실용적입니다. 안정적인 응답, 넓은 문맥 처리, 그리고 시제품부터 운영까지 이어지는 유연성이 필요할 때 유용합니다. 안정적인 응답, 넓은 문맥 처리, 그리고 시제품부터 운영까지 이어지는 유연성이 필요할 때 유용합니다. 안정적인 응답, 넓은 문맥 처리, 그리고 시제품부터 운영까지 이어지는 유연성이 필요할 때 유용합니다.

Input

$0.15/1M

Output

$0.60/1M

Cached

$0.01/1M

Batch

$0.04/1M

Calculate your Mistral Small 4 bill.

Set your workload — see cost at your exact volume.

What would Mistral Small 4 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Mistral Small 4 at a glance.

Memory

262,144

tokens

Max reply

32,768

tokens

Memory tier

Large

an entire book or large codebase

Tokenizer

mistral

Released

Mar 2026

Training cutoff

Oct 2025

Availability

Public pricing

Status

active

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 4

  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • Long documents, full codebases, or extensive chat histories.
  • High-volume workloads where unit cost matters.

When to look elsewhere

  • Very latency-sensitive, real-time apps where every millisecond counts.

FAQ

Mistral Small 4 — 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 4 costs roughly $35 per month. Input is $0.15 /1M tokens and output is $0.60 /1M tokens.
Mistral Small 4 has a 262,144-token context window (large memory — an entire book or large codebase). That means you can fit about 49,152 words of input and history in a single call.
Beyond text generation, Mistral Small 4 supports understanding images, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Mistral Small 4 was released in March 2026, with training data cut off around October 2025.
Models in a similar class include Ministral 3 8B 2512, Ministral 3 14B 2512, Mistral Large 3 2512. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Mistral Small 4 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.