Codestral 2
Codestral 2 is Mistral AI's language model with a 128K context window, starting at $0.3 / 1M input and $0.9 / 1M output. The second generation of Mistral AI's Codestral code-focused language model, designed for low-latency coding assistance.
| Specifications | |
|---|---|
mistral-codestral-2 | |
| Language | |
| Active | |
| Mistral AI | |
| 128K tokens | |
| Text | |
| Text | |
Capabilities
Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.3 | $0.9 | |
Cost Calculator
US Dollar ($)
Preset:
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Codestral 2 | — | 128K | $0.300 | $0.900 | Current |
| Codestral | 256K | $0.200 | $0.600 | Deprecated | |
| Mamba Codestral 7B | — | 256K | $0.250 | $0.250 | Deprecated |
| Mamba Codestral 7B | — | 256K | $0.190 | $0.190 | Available |