Codestral 22B is 89% cheaper than Grok 2 on blended 3:1 token pricing. Grok 2 costs $2.00/1M in and $10.00/1M out, while Codestral 22B costs $0.30/1M in and $0.90/1M out.
Grok 2 vs Codestral 22B
Compare verified input/output token rates, prompt caching discounts, latency tiers, and context limits between xAI and Mistral AI.
| Metric / Feature | Grok 2 (xAI) | Codestral 22B (Mistral AI) |
|---|---|---|
| Input Price ($ / 1M Tokens) | $2.00 | $0.30 |
| Output Price ($ / 1M Tokens) | $10.00 | $0.90 |
| Prompt Caching Input Rate | Not Available | Not Available |
| Blended 3:1 Rate (Production) | $4.000 / 1M | $0.450 / 1M |
| Max Context Window | 131k | 128k |
| Multimodal Vision | ✅ Supported | ❌ Text Only |
| MMLU Benchmark | 87.5% | 81.1% |
| Throughput & Latency | Fast (~45 t/s) | Ultra-Fast (~80 t/s) |
| Best For | Real-time news synthesis, coding, uncensored creative reasoning | Fill-in-the-middle code completion, automated unit tests, IDE integration |
When to Choose Grok 2
Choose Grok 2 if your workload requires real-time news synthesis, coding, uncensored creative reasoning. Ideal for teams needing xAI's infrastructure and ecosystem tooling.
When to Choose Codestral 22B
Choose Codestral 22B if your primary objective is fill-in-the-middle code completion, automated unit tests, ide integration. Ideal for scaling high-throughput pipelines with Mistral AI.
Want to compare Grok 2 against another model?
Select another target model to view immediate pricing & latency trade-offs.