Codestral
MistralMistral's dedicated coding model. Open-weight and highly optimized for code generation and completion.
Codestral Pricing
| Token Type | Price per Million |
|---|---|
| Input tokens | $0.300 |
| Output tokens | $0.900 |
Estimated Cost by Project Size
Realistic cost estimates for common coding scenarios. Assumes 30% cache hit rate where caching is available.
| Scenario | Token Usage | Estimated Cost |
|---|---|---|
| Small Script (1K lines) | 50K input / 30K output | $0.04 |
| Medium Feature (10K lines) | 500K input / 200K output | $0.29 |
| Large Project (50K lines) | 2,500K input / 1,000K output | $1.43 |
| Code Review (5K lines) | 250K input / 25K output | $0.07 |
Get Access to Codestral
Ready to start using Codestral? Get API access directly from Mistral.
Get API Access →How Does Codestral Compare?
| Model | Input ($/M) | Medium Feature Cost | |
|---|---|---|---|
| Codestral | $0.300 | $0.29 | selected |
| DeepSeek V3.2 | $0.300 | $0.34 | Compare |
| Grok 3 Mini | $0.300 | $0.21 | Compare |
| Qwen Coder Turbo V2 | $0.300 | $0.34 | Compare |
| DeepSeek Chat V3 | $0.270 | $0.31 | Compare |
| DeepSeek Coder V2 | $0.270 | $0.31 | Compare |
Related Models
Claude Sonnet 4
AnthropicAnthropic's balanced model for coding and general tasks. Best price-performance ratio in the Claude family.
Claude Opus 4
AnthropicAnthropic's most powerful model. Best for complex reasoning and challenging coding tasks.
Claude 3.5 Sonnet
AnthropicPrevious generation Sonnet. Still excellent for coding tasks at the same price point.
GPT-4o
OpenAIOpenAI's flagship multimodal model. Strong coding and reasoning at competitive pricing.