Models/Mistral/Codestral 2508

Codestral 2508

Name: Codestral 2508 API access
Brand: Mistral

Mistral · Proprietary · Released Aug 1, 2025 · mistralai/codestral-2508

Best $0.30 in / $0.90 out via Mistral

Compare Estimate cost

256K contextToolsStructured outputPrompt caching

Available from 2 providersUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 16 DAYS AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Mistralmistral1ST PARTY	$0.30	$0.90	$0.03	256K	—	0.73s	132 tok/s	100.0%
Mistralmistral/eu1ST PARTY	$0.33	$0.99	$0.033	256K	—	—	—	100.0%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 16 days ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

Pricing variants · USD / MTok in / out

STANDARD

$0.30 / $0.90

per MTok in / out

BATCH

$0.15 / $0.45

async batch

CACHE READ $0.03

About

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

Specifications

Context window256,000

Max output204,800

Modalities intext, file

Modalities outtext

LicenseProprietary

ReleasedAug 1, 2025

Knowledge cutoff2025-03-31

TokenizerMistral

Mistral Large 4$0.68 / $2.09 Mistral Medium 3.5$1.50 / $7.50 Mistral Small 4$0.15 / $0.60 Devstral 2 2512$0.40 / $2.00

Embed badge

[![Codestral 2508](https://modelindex.ai/badge/mistralai/codestral-2508)](https://modelindex.ai/models/mistralai/codestral-2508)

Sources

OpenRouter API23 minutes ago

AGGREGATOR

ModelIndex benchmarks16 days ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.