Mistral Medium 3.5
mistral-medium-3-5Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... Built by Mistral AI.
Prices updated
Input price
$1.50
per 1M tokens · Standard
Output price
$7.50
per 1M tokens · Standard
Input limit
262K
tokens
Output limit
210K
tokens
Input formats
Output formats
Mistral Medium 3.5 price history
2 price records since 9/25/2026
Mistral Medium 3.5 cost calculator
$68/month
Standard pricing
Overview
What is Mistral Medium 3.5?
Mistral Medium 3.5 is a text & reasoning and vision model from Mistral AI. Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex... Its 262K context window and $1.50 input price make it a candidate for quality-focused production applications.
Benchmarks
Mistral Medium 3.5 benchmarks & speed
How Mistral Medium 3.5 scores on standardized evaluations, and where it lands among every model we track.
14.2
Intelligence Index
166tok/s
Output speed
1125
DesignArena Elo
Reasoning
GPQA Diamond
74.8%
Graduate-level scientific reasoning · top 64%
HLE
13.8%
Humanity's Last Exam · top 58%
Coding
SciCode
40.2%
Python for scientific computing · top 78%
Latency & design
- Time to first token
- 2.21s
- DesignArena win rate
- 41.1%
- Design battles judged
- 10,894
Independent scores from Artificial Analysis and DesignArena · updated 10/8/2026. Higher is better; ranks compare against every model we track with that score.
Rates
Mistral Medium 3.5 pricing
Pricing is based on token usage. Provider-specific caching, batch, regional, and tool charges may affect the final cost.
Input · Standard
$1.50
Per 1M tokens
Cached input · Standard
Not available
No listed cached-input rate
Capabilities
Mistral Medium 3.5 Tools
Tools available when using Mistral Medium 3.5 through supported provider APIs.
Function calling
Supported
Structured outputs
Supported
JSON mode
Supported
Reasoning
Supported
Built-in web search
Not supported
Log probabilities
Not supported
Deterministic seed
Supported
Parallel tool calls
Not supported
Prompt caching
Not supported
Strengths and limitations
Strengths
- Measured results (AA Intelligence 14.2 · DesignArena Elo 1125) position it for demanding production work.
- 262K context supports large documents, repositories and extended conversations.
- Supports text & reasoning and vision workloads in one model.
Limitations
- Generated tokens cost 5× more than input tokens, which matters for verbose responses.
- Large context capacity does not guarantee consistent retrieval across the entire prompt.
- Arena Elo and MMLU-Pro are directional; test accuracy, latency and reliability on your own workload before committing.
Arena Elo, MMLU-Pro and pricing figures are illustrative; validate current vendor terms before purchase.
Same provider