Back to Models

Mistral Small 4

![Mistral](https://artificialanalysis.ai/_next/image?url=%2Fimg%2Flogos%2Fmistral_small.png&w=32&q=75)Mistral
28/ 57

Intelligence Score

Intelligence

28

#87 of 203 (top 43%)

Speed

160 tok/s

#30 of 131

Price

$0.26

per M tokens

#35 cheapest of 136

Context Window

256K

tokens

Latency: 1ms (#17)

Score Breakdown

Quality Score47%
Speed Score23%
Cost Score98%

Similar Models

Nemotron Cascade 2 30B A3B

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

28intelligence

Qwen3 Coder Next

![Alibaba](https://artificialanalysis.ai/img/logos/alibaba_small.svg)Alibaba

28intelligence

Nova 2.0 Omni (medium)

![Amazon](https://artificialanalysis.ai/img/logos/aws_small.svg)Amazon

28intelligence

DeepSeek V3.2 Speciale

![DeepSeek](https://artificialanalysis.ai/img/logos/deepseek_small.svg)DeepSeek

29intelligence

ERNIE 5.0 Thinking Preview

![Baidu](https://artificialanalysis.ai/img/logos/baidu_small.svg)Baidu

29intelligence

Use This Model

Claude Code

claude --model mistral-small-4

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "mistral-small-4",
    "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("mistral-small-4"),
  prompt: "Hello",
});
Back to Models