AI model reference · 2026
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.
- Context window
- 256,000 tokens
- Maximum output
- Not available
- Base provider API input
- $0.30 / 1M tokens
- Base provider API rate
- Published evidence
- Not available
Overview
About Codestral 2508
A concise catalog overview. Technical limits and published evaluation evidence are listed separately below.
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.
Published evaluations
Benchmark results
Only results mapped to this exact model and backed by a named source appear here. Different evaluation protocols are not treated as interchangeable.
No reviewed benchmark result is available for this exact model yet. We leave this section empty instead of assigning a nearby model’s score.
Human preference
Arena results
Arena scores come from blind human preference votes. They are reported separately from task benchmarks and are not used as substitutes for missing benchmark results.
No exact Arena match is available for this model. Similar names and provider variants are not merged automatically.
Technical reference
Specifications and API facts
Technical limits and reference provider prices come from the current catalog unless a reviewed external source is listed. Missing values stay marked as unavailable.
- Provider
- Mistral AI
- Release date
- Not available in reviewed sources
- Catalog added
- Aug 1, 2025
- Context window
- 256,000 tokens
- Maximum output
- Not available
- Knowledge cutoff
- 2025-03-31
- License
- Not available in reviewed sources
- Input types
- Text, File
- Output types
- Text
- Reasoning
- Not supported
- Provider endpoint tool parameters
- Accepts tool parameters
- Base provider API input
- $0.30 / 1M tokens
- Base provider cached input
- $0.03 / 1M tokens
- Base provider API output
- $0.90 / 1M tokens
These are reference provider API rates, not Writingmate checkout charges. Access in Writingmate follows the allowances of your Writingmate plan.
Provenance
Sources and update status
Source links are attached to the facts and evaluations they support. Catalog-only values are not presented as independently verified claims.
Evidence update date is not available.
Catalog record updated Aug 1, 2025.
Catalog-added dates describe when a model entered the catalog, not necessarily its public release date.
Keep exploring
Related models and comparisons
Open another model’s detail page or compare it directly with Codestral 2508. Suggestions come from the current catalog.
Wan 3.0
Alibaba
Wan 3.0 is a video generation model from Alibaba for text-to-video, image-to-video, and reference-guided video generation.
Avatar IV
Heygen
HeyGen: Avatar IV is an image-to-video model that animates a single photo into an expressive, lip-synced talking-head video.
Muse Spark 1.2 Contributor
Meta
Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost.
DeepSeek V4 Flash Vision Exp
DeepSeek
DeepSeek V4 Flash Vision Exp is a model by DeepSeek.
Ox Alpha
Stealth
Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads.
Hy-MT2-1.8B
Tencent
Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent.
Try Codestral 2508 in Writingmate
Use this model, then compare its response with other AI models in the same workspace.