← Back to all comparisons
Side-by-side
Llama 3.3 70B (Groq) vs Codestral
Groq vs Mistral — head-to-head specs and pricing.
Groq
Llama 3.3 70B (Groq)
Llama at Groq speed.
Meta's Llama 3.3 70B served on Groq's LPUs — hundreds of tokens/sec.
Mistral
Codestral
Low-latency code completion from Mistral.
Codestral — purpose-built for code completion and instruction in 80+ programming languages.
| Spec | Llama 3.3 70B (Groq) | Codestral |
|---|---|---|
| Provider | Groq | Mistral |
| Input cost / 1M tokens | $0.71 | $0.24 |
| Output cost / 1M tokens | $0.95 | $0.72 |
| Context window | 128,000 tokens | 32,000 tokens |
| Max output tokens | — | — |
| Streaming support | ✓ | ✓ |
| Tool calling | ✓ | — |
| Vision input | — | — |
| JSON mode | — | — |
| Status | ACTIVE | ACTIVE |
Use both via OneAPIKey — one key, one bill
OneAPIKey aggregates Groq, Mistral, and 10 more providers behind a single API. Smart Routing automatically picks the best model per request — or you choose explicitly.