Codestral
Autocomplete and fill-in-the-middle code generation at low cost.
What are Codestral's specs and price?
Codestral, built by Mistral, ships a 256K-token context window and a 33K-token max output, released 2025-09. It supports text input and costs $0.45 per million blended tokens, the 8th-cheapest of 32 models we track.
Specs
| Context window | 256K tokens |
| Max output | 33K tokens |
| Modalities | text |
| Extended thinking | No |
| Released | 2025-09 |
| Knowledge cutoff | 2025-06 |
| Provider | Mistral |
Verified 2026-08-08 — source.
Where it ranks
Strengths
- Code-specialised training
- Fast, low-cost completions
- Wide language coverage
More about Codestral
FAQ
What is Codestral's context window?
Codestral has a 256K-token context window and a 33K-token max output — the 16th-largest context of the 32 current models we track. Source: https://docs.mistral.ai/getting-started/models/, verified 2026-08-08.
Does Codestral support vision or audio input?
No — Codestral is text-only as of 2026-08-08.
Does Codestral have a reasoning or extended-thinking mode?
No — Codestral does not expose a separate reasoning/extended-thinking mode.
When was Codestral released, and what is its knowledge cutoff?
Codestral was released 2025-09 with a knowledge cutoff of 2025-06.
How much does Codestral cost, and who provides it?
Codestral is served by Mistral at $0.45/M blended tokens (3:1 input:output) — the 8th-cheapest of 32 current models. Full pricing breakdown: /llm-api-pricing/codestral.