Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Codestral 2508 (batch)

Mistral· released 1 Aug 2025

mistralai/codestral-2508:batch
Input / 1M tokens
$0.15
Output / 1M tokens
$0.45
Context window256K tokens

Longest answer: 205K tokens

reads textreads filetool calling
See it on openrouter.ai

About

Codestral 2508 (batch) is Mistral’s coding-focused language model, listed for tasks including fill-in-the-middle, code correction, and test generation. The summary describes it as intended for low-latency, high-frequency work. It accepts text and files and returns text, with tool support. Its context window is 256,000 tokens, and the maximum output is 204,800 tokens. The listed input price is USD 0.15 per 1M tokens, while output is USD 0.45 per 1M tokens. Its model ID is mistralai/codestral-2508:batch, and the release date is 2025-08-01. The batch designation is part of the listed entry name and identifier. For teams assessing coding-model integrations, the stated task focus, file input, context size, and token rates give concrete parameters for evaluating fit.

Who it is for

It suits developers building text- and file-based coding workflows involving code completion, correction, or test generation. Tool support may also fit integrations that call tools as part of those workflows.

What is good

  • Coding focus includes correction and test generation
  • Accepts text and file inputs
  • Supports tools
  • 256,000-token context window

What to know first

  • Output costs USD 0.45 per 1M tokens
  • Inputs are limited to text and files

Verdict

Codestral 2508 (batch) is aimed at coding tasks and supports file input, tools, and a substantial listed context window. Compare the listed batch endpoint’s capabilities and token rates with the needs of the intended workflow.

Details

Lab
Mistralopenrouter.ai · 3 Oct 2026
Context
256Kopenrouter.ai · 3 Oct 2026
Input price
$0.15 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.45 / 1Mopenrouter.ai · 3 Oct 2026
Max output
204,800 tokensopenrouter.ai · 3 Oct 2026
Inputs
text, fileopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources