codestral-2508 · Mistral AI
Mistral code-specialized route with file input and a 256K context window.
Last checked Aug 26, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Note: Live OpenRouter route snapshot checked 26 Aug 2026. Direct Mistral pricing and availability may differ. Confirm the current rate at the official provider source.
Quick answer
At the published base rate, Codestral 2508 (OpenRouter) costs $0.30 per 1M input tokens and $0.90 per 1M output tokens. It supports a 256K context window and is currently marked ga.
Method & trust
This rate card uses the provider's listed base input, output, and cached-input prices. Workload tables below apply those rates to explicit token counts, cache assumptions, and request volumes; verify provider-specific tiers before committing budget.
Input
$0.30
per 1M tokens
Output
$0.90
per 1M tokens
Cached input
$0.03
per 1M tokens
Context window
256K
max output 204.8K
Codestral 2508 (OpenRouter) cost calculator
What Codestral 2508 (OpenRouter) costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.000703 | $21.105 |
| RAG / search-augmented answers | 8,000 | 500 | $0.00177 | $53.10 |
| AI coding assistant | 12,000 | 2,000 | $0.003456 | $103.68 |
| Document summarization | 25,000 | 600 | $0.007365 | $220.95 |
| Agentic workflow | 40,000 | 1,500 | $0.00633 | $189.90 |
| Content generation | 800 | 1,200 | $0.001255 | $37.656 |
| Data extraction & tagging | 2,000 | 250 | $0.000717 | $21.51 |
| Translation | 5,000 | 5,500 | $0.006248 | $187.425 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| Codestral 2508 (OpenRouter) | $0.30 | $0.90 | 256K | $0.00138 |
| GPT-5.6 Solcompare | $5.00 | $30.00 | 1.1M | $0.035 |
| GPT-5.6 Terracompare | $2.00 | $12.00 | 1.1M | $0.014 |
| GPT-5.6 Lunacompare | $0.20 | $1.20 | 1.1M | $0.0014 |
| GPT-5.6 Cybercompare | $12.50 | $75.00 | 1.1M | $0.0875 |
| GPT-5.5 Standardcompare | $5.00 | $30.00 | 512K | $0.035 |
| GPT-5.5 Procompare | $30.00 | $180.00 | 512K | $0.21 |
| GPT-5.4 Workhorsecompare | $2.50 | $15.00 | 256K | $0.0175 |
| GPT-5.4 minicompare | $0.75 | $4.50 | 256K | $0.00525 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
Codestral 2508 (OpenRouter) costs $0.30 per 1M input tokens and $0.90 per 1M output tokens, with cached input at $0.03 per 1M tokens. Verified Aug 26, 2026 against https://openrouter.ai/api/v1/models.
Codestral 2508 (OpenRouter) supports a 256,000-token context window with up to 204,800 output tokens per request, tokenized with mistral_bpe.
At $0.30/M input and $0.90/M output, Codestral 2508 (OpenRouter) sits below GPT-5.6 Sol ($5.00/M in, $30.00/M out) — see the comparison table for full-workload differences.