mistralai
Mistral: Codestral Embed 2505
mistralai/codestral-embed-2505
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
mistralai/codestral-embed-2505 is a text-to-embeddings model from Mistral listed in the OpenRouter catalog. According to the catalog description, it is purpose-built for code and intended for embedding code databases and repositories and for supporting retrieval in coding assistants. The listing reports an 8192-token context length, text input, and embedding output, but provides no benchmark results or independent model card. All capability claims here come from the catalog alone and were not independently verified in this source pack.[1]
Strengths
Limitations
- Evidence is catalog-only: this source pack includes no independent model card or evaluation results, so the stated capabilities are unverified.[1]
- No benchmarks are listed; retrieval quality should be validated on your own workloads before adoption.[1]
- Supported parameters are listed as empty and no knowledge cutoff is given, so those details are unknown.[1]
Where to use it
- Candidate for embedding code repositories and code databases when a code-specialized embedding model is wanted; validate quality on your own data.[1]
- Possible option for the retrieval backend of coding assistants, as suggested by the catalog description.[1]
- Worth evaluating for semantic code search over large repositories.[1]
Sources
- [1] OpenRouter catalog · Mistral: Codestral Embed 2505Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Mistral Codestral Embed is specially designed for code, perfect for embedding code databases, repositories, and powering coding assistants with state-of-the-art retrieval.
Specifications
- Model ID
- mistralai/codestral-embed-2505
- Creator
- mistralai
- Added to OpenRouter
- 30.10.2025
- Context length
- 8,192
- Modality
- text->embeddings
- Input modalities
- text
- Output modalities
- embeddings
- Token pricing
- USD per 1M tokens: in $0.150 / out $0
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | — |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | output: embeddings |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 8,192 | $0.150 | $0 | — | — | — |
| Mistral | 8,192 | $0.165 | $0 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.