← Back to all comparisons
Side-by-side
Claude Sonnet 4.6 vs Codestral
Anthropic vs Mistral — head-to-head specs and pricing.
Anthropic
Claude Sonnet 4.6
Balanced speed + capability.
Sonnet is Anthropic's balanced model for general agents and chat.
Mistral
Codestral
Low-latency code completion from Mistral.
Codestral — purpose-built for code completion and instruction in 80+ programming languages.
| Spec | Claude Sonnet 4.6 | Codestral |
|---|---|---|
| Provider | Anthropic | Mistral |
| Input cost / 1M tokens | $3.60 | $0.24 |
| Output cost / 1M tokens | $18.00 | $0.72 |
| Context window | 200,000 tokens | 32,000 tokens |
| Max output tokens | 16,000 | — |
| Streaming support | ✓ | ✓ |
| Tool calling | ✓ | — |
| Vision input | ✓ | — |
| JSON mode | — | — |
| Status | ACTIVE | ACTIVE |
Use both via OneAPIKey — one key, one bill
OneAPIKey aggregates Anthropic, Mistral, and 10 more providers behind a single API. Smart Routing automatically picks the best model per request — or you choose explicitly.