Should you use Codestral (latest)?
Codestral (latest) is listed for chat workloads and supports a 256K context window.
Use it when LLM7.io's free tier is enough for evaluation, demos, or light production traffic.
Mistral code model for completions, refactors, and developer IDE workflows
https://api.llm7.io/v1 codestral-latest | Benchmark | Score | Metric | Date |
|---|---|---|---|
| Aider Polyglot | 11.1 | percent correct | 2025-01-13 |
Codestral (latest) is listed for chat workloads and supports a 256K context window.
Use it when LLM7.io's free tier is enough for evaluation, demos, or light production traffic.
We only found this Codestral (latest) listing on LLM7.io in the current catalog. Use the related models section for nearby alternatives.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | Codestral (latest) | Free tier | 256K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| deepseek-r1-0528 | LLM7.io | 131K | Check provider |
| deepseek-v3-0324 | LLM7.io | 131K | Check provider |
| gpt-4o-mini | LLM7.io | 131K | Check provider |
| mistral-small-3.1-24b | LLM7.io | 32K | Check provider |
| qwen2.5-coder-32b | LLM7.io | 131K | Check provider |
Codestral (latest) is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
Codestral (latest) is listed with free API access on LLM7.io, subject to the provider's quota and account policy.
The model ID shown in this catalog is codestral-latest.
The listed context window is 256K tokens with up to 4K output tokens.
Free Codestral (latest) API.
For API keys, setup steps, and provider-level limits, see the LLM7.io provider page.