Mistral: Devstral Medium

Public pricingIntelligence 77/100Medium memory도구 활용

Mistral: Devstral Medium은 코딩, 소프트웨어 엔지니어링, 에이전트 워크플로에 맞춘 텍스트 모델입니다. 강력한 코딩 성능、안정적인 도구 사용과 에이전트 동작, 131K tokens의 컨텍스트, 균형형 비용 특성을 결합해 코딩, 소프트웨어 엔지니어링, 에이전트 워크플로에서 안정적인 작업을 돕습니다. 특히 정확도, 문맥, 제어가 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.

Input

$0.40/1M

Output

$2.00/1M

Cached

$0.04/1M

Batch

$0.20/1M

Calculate your Devstral Medium bill.

Set your workload — see cost at your exact volume.

What would Devstral Medium cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Devstral Medium at a glance.

Memory

131,072

tokens

Max reply

32,768

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

mistral

Released

Jul 2025

Training cutoff

Mar 2025

Availability

Public pricing

Status

active

Benchmarks

Quality benchmarks

Independent evaluations from public leaderboards. Higher is better.

  • swe_bench_verified

    61.6

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 Devstral Medium

  • 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

Devstral Medium — 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, Devstral Medium costs roughly $110 per month. Input is $0.40 /1M tokens and output is $2.00 /1M tokens.
Devstral Medium has a 131,072-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,576 words of input and history in a single call.
Beyond text generation, Devstral Medium supports calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Devstral Medium was released in July 2025, with training data cut off around March 2025.
Models in a similar class include Devstral 2 2512, Mistral Medium 3, Mistral Medium 3.1. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Devstral Medium 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