The Orchestrator › Models › Mistral AI
Mistral AI: Mistral: Mistral Medium 3.5
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...
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/mistral-medium-3-5 |
| Context window | 262K tokens (262,144) |
| Modalities | text + image + file → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2026-04-30 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/mistral-medium-3-5 | $1.50 | $7.50 | 262K |
| batch | OpenRouter | mistralai/mistral-medium-3-5:batch | $0.75 | $3.75 | 262K |
| standard | Vercel AI Gateway | mistralai/mistral-medium-3.5 | $1.50 | $7.50 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.50 | $7.50 | 262K |
| 2026-11-14 | $1.50 | $7.50 | 262K |
Capabilities
Vision (image input)File inputAgentic tool useStructured outputs256K+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, reasoning_effort, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p