Back to models
retired
Mistral: Codestral 2508
mistral/codestralPrices
- Input
$0.30 per 1M tokens
high- Input (cached read)
$0.03 per 1M tokens
high- Output
$0.90 per 1M tokens
high
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Google Vertex AI | Input | $0.20 per 1M tokens |
| Output | $0.60 per 1M tokens | |
| Microsoft Azure | Input | $0.30 per 1M tokens |
| Output | $0.90 per 1M tokens | |
| Microsoft Azure · azure-ai | Input | $0.30 per 1M tokens |
| Output | $0.90 per 1M tokens | |
| OpenRouter · mistral | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| OpenRouter · mistralai | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| OpenRouter | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| Other · edenai | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| Other · kilo | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| Other · llmgateway-providers | Input | $0.30 per 1M tokens |
| Output | $0.90 per 1M tokens | |
| Other · merge-gateway | Input | $0.30 per 1M tokens |
| Output | $0.90 per 1M tokens | |
| Other · nano-gpt | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.15 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| Other · openrouter | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens | |
| Other · vercel | Input | $0.30 per 1M tokens |
| Input (cached read) | $0.03 per 1M tokens | |
| Output | $0.90 per 1M tokens |
Specifications
- Provider
- mistral
- Context window
- 256,000
- Max output tokens
- 204,800
- Open weights
- yes
- Released
- 05/29/2024
- Retires
- 06/16/2025
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.3 per 1M tokens, unchanged since 09/14/2026
- Output
- 0.9 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.03 per 1M tokens, unchanged since 09/14/2026