Codestral 22B is 79% cheaper than Gemini 1.5 Pro on blended 3:1 token pricing. Gemini 1.5 Pro costs $1.25/1M in and $5.00/1M out, while Codestral 22B costs $0.30/1M in and $0.90/1M out.
Gemini 1.5 Pro vs Codestral 22B
Compare verified input/output token rates, prompt caching discounts, latency tiers, and context limits between Google and Mistral AI.
| Metric / Feature | Gemini 1.5 Pro (Google) | Codestral 22B (Mistral AI) |
|---|---|---|
| Input Price ($ / 1M Tokens) | $1.25 | $0.30 |
| Output Price ($ / 1M Tokens) | $5.00 | $0.90 |
| Prompt Caching Input Rate | $0.312/1M | Not Available |
| Blended 3:1 Rate (Production) | $2.188 / 1M | $0.450 / 1M |
| Max Context Window | 128k | 128k |
| Multimodal Vision | ✅ Supported | ❌ Text Only |
| MMLU Benchmark | 85.9% | 81.1% |
| Throughput & Latency | Standard (~35 t/s) | Ultra-Fast (~80 t/s) |
| Best For | Massive codebase analysis, hours of video comprehension, full book translation | Fill-in-the-middle code completion, automated unit tests, IDE integration |
When to Choose Gemini 1.5 Pro
Choose Gemini 1.5 Pro if your workload requires massive codebase analysis, hours of video comprehension, full book translation. Ideal for teams needing Google'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 Gemini 1.5 Pro against another model?
Select another target model to view immediate pricing & latency trade-offs.