Codestral Embed
Mistral AI’s code embedding model, released 2025-05-28; status: generally available.
At a glance
- Context window
- 8K tokens
- Max output
- —
- Text input / output · per 1M tokens
- $0.150 / —
- Knowledge cutoff
- —
API pricing
Listed text rates, USD per million tokens · effective 2025-05-28
- Input
- $0.15
- Output
- —
Specifications
- Provider
- MistralAI
- Model type
- Embedding model
- Released
- May 28, 2025
- Architecture
- Undisclosed
- Context window
- 8K tokens
- Input
- Text
- Weights
- Closed / API only
- Commercial use
- Proprietary
Model analysis
Codestral Embed is Mistral AI’s code embedding model: released 2025-05-28 per the official Mistral model card; API ID codestral-embed-2505; context window 8k; license: Proprietary (Mistral commercial terms).
Current status: generally available
The status comes from the lifecycle shown in Mistral Docs. Mistral has not published the parameter count, so the fields are left blank rather than estimated. Note: Current code embedding model. This entry is based on the official model page only; independent benchmarks and pricing have not been added.
Source: Mistral official page. Retrieved 2026-10-06.
Last reviewed 2026-10-07
Primary sources
- Codestral Embed technical reportdocs.mistral.ai
Community discussion
Share the API, setup, and tradeoffs you actually tested. Rate the model once; comment as often as you like.
Used this model? Sign in with Google to rate it and share what worked, what did not, and which API or setup you tested.
No community comments yet.
