MultimodalAPI only

Mistral Medium 3.5

Mistral AI

Updated May 21, 2026 · Benchmarks via Artificial Analysis, specs & pricing via OpenRouter · Methodology · Report an error

Specifications

Type: Multimodal
Access: API only
Released: April 30, 2026
Context window: 262,144 tokens
Output speed: 140 tok/s
Latency (TTFT): 0.58s
Input: Text, Image
Output: Text
API pricing: $1.50 in · $7.50 out / 1M tokens

Capabilities

Function callingStructured output

Benchmarks

Reasoning

74.8

General

Humanity’s Last Exam

12.8

Compare Mistral Medium 3.5 with

vs Sonar Reasoning Pro vs R1 1776 vs Qwen3.7 Max vs Gemini 3.5 Flash

See all Mistral Medium 3.5 alternatives →