Mistral Medium 3.5: price, context window and capabilities
Mistral Medium 3.5 is a model from Mistral AI (mistralai/mistral-medium-3-5). It supports reasoning. It supports tool use. It costs $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window.
What it costs in practice
Using the listed prices: a chat turn of 2,000 input and 500 output tokens costs about $0.0067, so 10,000 such turns cost about $67.50. Summarising a 100,000-token document into 2,000 tokens costs about $0.165. A long agent run that reads 1 million tokens and writes 50,000 costs about $1.88.
How it compares
Among the 40 models we track, Mistral Medium 3.5 ranks #28 by input price and #31 by output price (1 is cheapest), and #31 by context window (1 is largest). Models with the same tool and reasoning support that cost less per output token: DeepSeek V4 Pro 0423 ($0.418), Qwen3.8 Omni Flash ($0.470), Qwen3.8 Flash ($0.470), GPT-6 Luna Pro ($0.500). Models with a larger context window at the same or lower output price: Llama 4 Scout (1.3M), GPT-6 Luna Pro (1.1M), GPT-6 Luna (1.1M), Gemini 3.8 Flash (1.0M).
More from Mistral AI
- Mistral Small 4: $0.150 in / $0.600 out, 262K context
- Devstral 2 2512: $0.400 in / $2.00 out, 262K context
- Ministral 3 14B 2512: $0.200 in / $0.200 out, 262K context
Prices and limits come from OpenRouter's public model catalogue, last synced 4 Oct 2026. Provider pricing can differ from OpenRouter's and changes often; confirm on the provider's own page before you commit. See the guide to choosing a model or the full comparison.
Feed, daily deep-dive and bytes — readable offline, with push alerts for the topics you follow.