Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Mistral AI APIThe lab's own API · cached $0.03 | $0.3 | $0.9 | $0.3 / $0.9List price | $0.03 | List price |
| Mistral AI eu · cached $0.033 | $0.33 | $0.99 | $0.33 / $0.99+10% vs list | $0.033 | +10% vs list |
USD per 1M tokens; batch $0.15 in, $0.45 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $48.00 direct.
Helicone$48.00+0%
Kong AI Gateway$48.00+0%
LiteLLM$48.00+0%
Vercel AI Gateway$48.00+0%
Cloudflare AI Gateway$50.40+5%
Requesty$50.40+5%
Eden AI$50.64+5.5%
OpenRouter$50.64+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| Mistral Medium 3.5 Mistral AI · 262K | $1.5 | $7.5 | $1.5 / $7.5 | $3 | 262K | Lab list price | · |
| Mistral Small 4 Mistral AI · 262K | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 262K | Lab list price | · |
| Devstral 2 2512 Mistral AI · 262K | $0.4 | $2 | $0.4 / $2 | $0.8 | 262K | on Mistral AI (eu) | · |
| Ministral 3 14B 2512 Mistral AI · 262K | $0.2 | $0.2 | $0.2 / $0.2 | $0.2 | 262K | Lab list price | · |
 GLM 5.3Z.ai · 1.31M | $0.561 | $1.76 | $0.561 / $1.76 | $0.862 | 1.31M | on Baidu (fp8) | · |
| GLM 4.6 Z.ai · 205K | $0.43 | $1.75 | $0.43 / $1.75 | $0.76 | 205K | on Venice (fp4) | · |
 DeepSeek V4.1 FlashDeepSeek · 1MCheapest: $0.131 on Morph | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.131 on Morph | · |
 Kimi K2.5Moonshot AI · 262K | $0.45 | $2.25 | $0.45 / $2.25 | $0.9 | 262K | on SiliconFlow (int4) | · |
About Codestral 2508
Mistral's cutting-edge language model for coding released end of July 2025.
Takes text, files in and returns text. First listed Aug 12, 2025. Up to 205K output tokens. Blended price $0.45 per 1M tokens at 3 input to 1 output. Model id codestral-2508.
Price history
List price since Aug 12, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does Codestral 2508 cost?
$0.3 per million input tokens and $0.9 per million output tokens, with cached input at $0.03, or $0.15 and $0.45 through the Batch API.
What is the context window of Codestral 2508?
256K tokens, with up to 205K tokens of output.
Where is Codestral 2508 cheapest?
Of 2 routes tracked, Mistral AI is cheapest at $0.3 input and $0.9 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.