Back to Models

Devstral 2

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral
22/ 57

Intelligence Score

Intelligence

22

#120 of 212 (top 57%)

Speed

68 tok/s

#91 of 141

Price

Free

per M tokens

Context Window

256K

tokens

Latency: 1ms (#39)

Score Breakdown

Quality Score37%
Speed Score9%
Cost Score100%

Similar Models

INTELLECT-3

![Prime Intellect](https://artificialanalysis.ai/img/logos/prime-intellect_small.svg)Prime Intellect

22intelligence

Solar Open 100B

![Upstage](https://artificialanalysis.ai/img/logos/upstage_small.svg)Upstage

22intelligence

Gemini 2.5 Flash-Lite (Sep)

![Google](https://artificialanalysis.ai/img/logos/google_small.svg)Google

22intelligence

K-EXAONE

![LG AI Research](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Flg_small.png&w=32&q=75)LG AI Research

23intelligence

GPT-5.4 mini

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

23intelligence

Use This Model

Claude Code

claude --model devstral-2

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "devstral-2",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("devstral-2"),
  prompt: "Hello",
});
Back to Models