mistralai

Mistral: Mistral Medium 3.1

Mistral Medium 3.1, developed by MistralAI, is equipped with a context length of 131,072 tokens and supports text, image, and file inputs; it also allows the integration of external tools but lacks advanced reasoning or structured output capabilities. The model's broad modalities make it versatile for various tasks, though its performance in complex reasoning is limited. Given its blended benchmark score of 21.4 across three independent evaluations, Mistral Medium 3.1 is suitable for projects that require a mix of text and image handling without the need for advanced reasoning or structured outputs. Its pricing at $0.4 per input token and $2.0 per output token makes it accessible for those on moderate budgets while still offering decent performance; however, users should consider its limitations in more complex tasks before shortlisting it.

Quality Score
95/100
price + capability + benchmarks
Input Price
$0.40
per 1M tokens
Output Price
$2.00
per 1M tokens
Context Window
131,072
tokens

Benchmark results

Independent, published benchmarks. Blended score 21.4 across 3 benchmarks, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 24.3
AI Index Coding software engineering tasks 33.8
AI Index Agentic multi-step tool-using tasks 10.1
Model ID
mistralai/mistral-medium-3.1
Vendor
mistralai
Released
August 2025
Tokenizer
Mistral
Input Modalities
text, image, file
Output Modalities
text
Max Output
default
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.40/M input and $2.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.01
Classify 1,000 customer emails 500k in / 50k out $0.30
A month of a busy support chatbot 5M in / 2M out $6.00

Similar models

Quick answers

How much does Mistral: Mistral Medium 3.1 cost?
$0.40 per million input tokens and $2.00 per million output tokens.
What is Mistral: Mistral Medium 3.1's context window?
131,072 tokens, roughly 196 pages of text in a single request.
Does Mistral: Mistral Medium 3.1 support tool calling?
It supports tool calling, structured output.
Can Mistral: Mistral Medium 3.1 process images?
Yes, it accepts image input.