ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Mistral AI
Proprietary API Mistral AI · mistral-medium-2508 · Text+Image

Mistral Medium 3.1 Official Specifications, Pricing & Benchmarks

Mistral Medium 3.1 (mistral-medium-2508) by Mistral AI, released 2025-08-12, featuring 262,144 context window, 262,144 max output tokens, and Text+Image input.

📋 Mistral Medium 3.1 Official API & System Card Specifications

Verified against official Mistral AI developer documentation & pricing

API Model ID: mistral-medium-2508

1. Identity & Capabilities

API Spec
API Model ID
mistral-medium-2508
Release Date
2025-08-12
Weight License
Proprietary (Undisclosed)
Native Reasoning
—
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
262,000 tokens (262K)
Max Output Tokens
262,144 tokens
Input Modalities
Text + Image
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Cloud API only (Proprietary)

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.4
Cached Input / 1M
$ 0.08 -80%
Output / 1M Tokens
$ 2

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Standard Generation Config
temperature=0.7 top_p=0.95 max_tokens=65,536

Closest Self-Hostable Open-Weight Alternatives to Mistral Medium 3.1

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Mistral Medium 3.1 open-source or proprietary?

Mistral Medium 3.1 (mistral-medium-2508) is a proprietary commercial model by Mistral AI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Mistral Medium 3.1?

Mistral Medium 3.1 supports 262K input context and 262,144 max output tokens, priced at $0.4/1M input ($0.08/1M cached) and $2/1M output.