Codestral 25.08
Release Date: Aug 1, 2025 Creator: Mistral AI
Codestral 2508 is Mistral’s high-performance model for code generation and completion. Optimized for low-latency workflows like fill-in-the-middle and rapid edits.
| Model Specifications | |
|---|---|
| Knowledge Cutoff | early 2025 |
| Context (VividLLM) | 64,000 Tokens |
| With a context window of 64,000 tokens, this model can 'remember' and analyze up to 96 pages of data at once. This makes it a top choice for processing technical manuals and multi-chapter reports. | |
| Context (Native) | 256,000 Tokens |
| Input Modalities | TextImagePDF |
| Output Type | Text |
| Max Output | 8192 |
| Input Weight | 0.80 x (Casual) |
| Output Weight | 0.67 x (Casual) |
| Industry Benchmarks | |
| Intelligence Index (Artificial Analysis) | N/A |
| Coding Index (Artificial Analysis) | N/A |
| Math Index (Artificial Analysis) | N/A |
| Response Speed | |
| Output Tokens per second | N/A |
| Median Time to First Token Seconds | N/A |
Launch VividLLM Now => :
Benchmarks accessed via : Artificial Analysis
Disclaimer: We are providing Image Upload options to only limit models as of now, so some models which have image upload options might now have that feature on our site.