Jahanzaib
Mistral: Devstral 2Work with me

Mistral: Devstral 2

byMistral

Devstral 2 is a language model from Mistral released on Dec 2, 2025. It reads text and writes text, with a 262K token context window and up to 262K tokens per reply.

Show more

It costs $0.40 per million input tokens and $2 per million output tokens.

It supports tool calling and structured JSON output, and its weights are open, so you can host it yourself.

This is the same model as Devstral 2, listed here under an earlier id. Prices and providers are kept current on that page.

Modalities
In / out price
$0.40 / $2 per 1M
Context
262K
Max output
262K
Released
Dec 2, 2025
Knowledge cutoff
Dec 2025
  • Tool calling
  • Structured output
  • Reasoning
  • Prompt caching
  • Open weights
  • Free to use

Devstral 2 pricing

USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.

Input$0.40 / 1M tokens
Output$2 / 1M tokens

What Devstral 2 costs per month

Pick a workload close to yours or type your own volumes.

Devstral 2 per month
$51.00
Without caching
$51.00
Per request
$0.0017

Supported request parameters

What you can set when you call Devstral 2 through an OpenAI compatible API.

  • Toolstools
  • Structured outputsstructured_outputs
  • Temperaturetemperature

Alternatives to Devstral 2

Models that take the same inputs and call tools, closest in price, cheaper ones first.

  • Mistral Large 3

    Reads text and images. Tool calling, structured output. Served by 15 providers.

    by mistralaiNov 1, 2024$0.50/M input tokens$1.50/M output tokens15 providers

  • Qwen3.7 Plus

    Index 25.2

    Reads text, images and video. Tool calling, structured output, reasoning. Served by 24 providers.

    by qwenJun 2, 20261M context$0.40/M input tokens$1.60/M output tokens24 providers

  • Meta: Muse Glimmer 30B

    Index 17.5

    Reads text and images. Tool calling, structured output, reasoning. Served by 12 providers.

    by metaAug 10, 2026131K context$0.35/M input tokens$1.50/M output tokens12 providers

  • Cohere: Command A+

    Index 13.1

    Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by cohereMay 20, 2026192K context$0.30/M input tokens$1.50/M output tokens2 providers

  • Google: Gemini 3.1 Flash Lite

    Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 25 providers.

    by googleFeb 18, 2026$0.25/M input tokens$1.50/M output tokens25 providers

  • Xiaomi: MiMo-V2.6-Pro

    Index 46.3

    Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 17 providers.

    by xiaomiSep 22, 20261.05M context$0.435/M input tokens$0.87/M output tokens17 providers

More from Mistral

  • Mistral Large 4

    Index 38.4

    Reads text and images. Tool calling, structured output, reasoning. Served by 8 providers.

    by mistralaiOct 6, 20261.05M context$0.68/M input tokens$2.09/M output tokens8 providers

  • Mistral Medium 3.5

    Index 14.2

    Reads text, images and files. Tool calling, structured output, reasoning. Served by 18 providers.

    by mistralaiApr 29, 2026262K context$1.50/M input tokens$7.50/M output tokens18 providers

  • Mistral Medium

    Reads text and images. Tool calling, structured output, reasoning. Served by 5 providers.

    by mistralaiApr 29, 2026$1.50/M input tokens$7.50/M output tokens5 providers

  • Mistral Small 4

    Index 11.3

    Reads text and images. Tool calling, structured output, reasoning. Served by 15 providers.

    by mistralaiMar 16, 2026262K context$0.15/M input tokens$0.60/M output tokens15 providers

  • Mistral Small

    Reads text and images. Tool calling, structured output, reasoning. Served by 4 providers.

    by mistralaiMar 16, 2026$0.15/M input tokens$0.60/M output tokens4 providers

  • Voxtral Mini TTS

    Speech

    Turns text into spoken audio.

    by mistralaiMar 1, 2026

All Mistral models

Devstral 2 questions

How much does the Devstral 2 API cost?

$0.40 per million input tokens and $2 per million output tokens. The estimator on this page turns that into a monthly bill for your own workload.

What is the context window of Devstral 2?

262,144 tokens of input, and it can write up to 262,144 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.

Does Devstral 2 support tool calling?

Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.

Is Devstral 2 open source?

Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.

When was Devstral 2 released?

Dec 2, 2025, with training data up to Dec 2025.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.

Building on Devstral 2?

I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.

Book Meeting