The Orchestrator › Models › Mistral AI
Mistral AI: Mistral: Codestral 2508
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Blog Post
Specifications
| Provider | Mistral AI |
| Model ID | mistralai/codestral-2508 |
| Context window | 256K tokens (256,000) |
| Modalities | text + file → text |
| Tokenizer | Mistral |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2025-08-01 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | mistralai/codestral-2508 | $0.3 | $0.9 | 256K |
| standard | TrustedRouter | mistralai/codestral-2508 | $0.317 | $0.95 | 256K |
| alias | Vercel AI Gateway | mistralai/codestral | $0.3 | $0.9 | 128K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.317 | $0.95 | 256K |
| 2026-11-14 | $0.3 | $0.9 | 256K |
Capabilities
File inputAgentic tool useStructured outputs256K+ context windowNo content storage (attested)Zero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, max_tokens, prediction, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p