Gemini 2.0 Flash is 89% cheaper than Claude 3.5 Haiku on blended 3:1 token pricing. Claude 3.5 Haiku costs $0.80/1M in and $4.00/1M out, while Gemini 2.0 Flash costs $0.10/1M in and $0.40/1M out.
Claude 3.5 Haiku vs Gemini 2.0 Flash
Compare verified input/output token rates, prompt caching discounts, latency tiers, and context limits between Anthropic and Google.
| Metric / Feature | Claude 3.5 Haiku (Anthropic) | Gemini 2.0 Flash (Google) |
|---|---|---|
| Input Price ($ / 1M Tokens) | $0.80 | $0.10 |
| Output Price ($ / 1M Tokens) | $4.00 | $0.40 |
| Prompt Caching Input Rate | $0.080/1M | $0.025/1M |
| Blended 3:1 Rate (Production) | $1.600 / 1M | $0.175 / 1M |
| Max Context Window | 128k | 128k |
| Multimodal Vision | ❌ Text Only | ✅ Supported |
| MMLU Benchmark | 75.2% | 84.6% |
| Throughput & Latency | Ultra-Fast (~95 t/s) | Ultra-Fast (~110 t/s) |
| Best For | Real-time agents, code completion, fast document scanning | Real-time multimodal voice/video streaming, low-latency agent loops |
When to Choose Claude 3.5 Haiku
Choose Claude 3.5 Haiku if your workload requires real-time agents, code completion, fast document scanning. Ideal for teams needing Anthropic's infrastructure and ecosystem tooling.
When to Choose Gemini 2.0 Flash
Choose Gemini 2.0 Flash if your primary objective is real-time multimodal voice/video streaming, low-latency agent loops. Ideal for scaling high-throughput pipelines with Google.