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. [Blog Post](https://mistral.ai/news/codestral-25-08)

LLM & Generative AI 1 model 2 listings snapshot Oct 14, 2026, 12:43 AM

Platforms

click a card to open the detail table

Cheapest OpenRouter no official benchmark Input$0.150 Output$0.450 per 1M tokens Fastest OpenRouter lowest p50 latency on this board 128.1 ms p50 Most free quota — largest published free allowance — free tier

Model variants

W3r9 dedup — same model + identical tags merge; prices are listed per billing form

Model	Provider	Tags	Input /1M	Output /1M
mistralai/codestral-2508	OpenRouter	250k contextmultimodal	$0.300	$0.900
mistralai/codestral-2508:batch :batch	OpenRouter	250k contextmultimodal	$0.150	$0.450

Capabilities

official design_arena & architecture metadata

Design Arena Elo official design_arena benchmark (OpenRouter)

3d 1021 · 45.4% wr
dataviz 1019 · 41.1% wr
uicomponent 1019 · 46.7% wr
website 1015 · 37.8% wr
codecategories 1010 · 38.5% wr
gamedev 972 · 36.3% wr

Input / Output modalities modality: text+file->text

text in+out

Platform details

per provider

provider	model	Input /1M	Output /1M	Latency ?	Official $/1M	Availability	Data time
OpenRouter	mistralai/codestral-2508	$0.300	$0.900	128.1 ms	—	100% available	2026-10-14 00:43:21

1 rows · snapshot 2026-10-14 00:43:21 · from data/public/prices.json + measurements.json