Mistral: Codestral 2508 (batch)
mistralai/codestral-2508:batch
Description
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.
How this model compares
Overall covers the full catalog. By plan covers only models available on that tier (same rules as available models in your list). Position on min–average–max. Prices use the higher of prompt or completion per token, shown per 1M tokens.
Price (per 1M tokens)
Min
Max
This model
382 models in this groupPrice (per 1M tokens)
- Min
- $0.049
- Avg
- $11.48469
- Max
- $750.00
This model: $0.90 / 1M tokens
Context length (tokens)
Min
Max
This model
382 models in this groupContext length (tokens)
- Min
- 4,095 tokens
- Avg
- 471,837.01 tokens
- Max
- 2,000,000 tokens
This model: 256,000 tokens
Capabilities
text+file->textContext: 256,000 tokens
Input:
TextFile
Output:
Text