Mistral: Mistral Medium 3
mistralai/mistral-medium-3
147th smartest of 182ToolsJSONVision
Intelligence
12.5
147th of 182
Design Elo
—
Speed
—
tokens/sec
Latency
—
first token
Input price
$0.400
159th cheapest
Context
131K
How it compares
Smarter than19%
of all ranked models
Cheaper than52%
of all ranked models
Overview
Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...
Benchmarks
independent · Artificial Analysis & Design ArenaArtificial Analysis44th percentile
Intelligence Index
12.5
GPQA Diamond
58%
Humanity's Last Exam
4%
SciCode
33%
Tau²-Bench (agentic)
24%
Providers & pricing (1)
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Mistral | $0.400 | $2.00 | 131K | 100% |
Specifications
Context window131K
Max output—
Knowledge cutoffMar 2025
Input modalitiestext, image, file
Output modalitiestext
Prompt caching—
Cache read price$0.040/M
ModeratedNo
Mistral Medium 3 FAQ
How much does Mistral Medium 3 cost?
Mistral Medium 3 costs $0.400 per million input tokens and $2.00 per million output tokens via OpenRouter, making it 159th cheapest of 332 paid models.
How smart is Mistral Medium 3?
Mistral Medium 3 scores 12.5 on the Artificial Analysis Intelligence Index, ranking 147th of 182 benchmarked models, with a GPQA Diamond score of 58%.
What is Mistral Medium 3's context window?
Mistral Medium 3 supports a 131K-token context window. It accepts text, image, file input.
Similar models
All Mistral Medium 3 alternatives →Compare head-to-head
Mistral: Mistral Medium 3 vs Qwen: Qwen3 Coder 30B A3B InstructMistral: Mistral Medium 3 vs Qwen: Qwen3 Next 80B A3B InstructMistral: Mistral Medium 3 vs OpenAI: GPT-4o (2024-11-20)Mistral: Mistral Medium 3 vs OpenAI: GPT-4oMistral: Mistral Medium 3 vs Qwen: Qwen3 VL 32B InstructMistral: Mistral Medium 3 vs Z.ai: GLM 4.6V