Gemini 1.5 Flash is 92% cheaper than Claude 3.5 Haiku on blended 3:1 token pricing. Gemini 1.5 Flash costs $0.07/1M in and $0.30/1M out, while Claude 3.5 Haiku costs $0.80/1M in and $4.00/1M out.
Gemini 1.5 Flash vs Claude 3.5 Haiku
Compare verified input/output token rates, prompt caching discounts, latency tiers, and context limits between Google and Anthropic.
| Metric / Feature | Gemini 1.5 Flash (Google) | Claude 3.5 Haiku (Anthropic) |
|---|---|---|
| Input Price ($ / 1M Tokens) | $0.07 | $0.80 |
| Output Price ($ / 1M Tokens) | $0.30 | $4.00 |
| Prompt Caching Input Rate | $0.019/1M | $0.080/1M |
| Blended 3:1 Rate (Production) | $0.131 / 1M | $1.600 / 1M |
| Max Context Window | 128k | 128k |
| Multimodal Vision | ✅ Supported | ❌ Text Only |
| MMLU Benchmark | 78.9% | 75.2% |
| Throughput & Latency | Ultra-Fast (~100 t/s) | Ultra-Fast (~95 t/s) |
| Best For | High-frequency API calls, audio processing, bulk document summarization | Real-time agents, code completion, fast document scanning |
When to Choose Gemini 1.5 Flash
Choose Gemini 1.5 Flash if your workload requires high-frequency api calls, audio processing, bulk document summarization. Ideal for teams needing Google's infrastructure and ecosystem tooling.
When to Choose Claude 3.5 Haiku
Choose Claude 3.5 Haiku if your primary objective is real-time agents, code completion, fast document scanning. Ideal for scaling high-throughput pipelines with Anthropic.
Want to compare Gemini 1.5 Flash against another model?
Select another target model to view immediate pricing & latency trade-offs.