claude-haiku-5-5 vs gemini-2.5-flash
Anthropic against Google Gemini, priced on the same four workloads with price book 2026-10-22.
On real workloads
| Workload | claude-haiku-5-5 per call | gemini-2.5-flash per call | Monthly difference |
|---|---|---|---|
| Chat reply 1,500 input and 400 output tokens, 100,000 calls a month |
$0.00035 | $0.00145 | $110.00 |
| RAG answer, cached context 2,000 fresh + 4,000 cached input, 500 output, 100,000 calls a month |
$0.00049 | $0.00197 | $148.00 |
| Agent step 4,000 fresh + 8,000 cached input, 800 output, 250,000 calls a month |
$0.00088 | $0.00344 | $640.00 |
| Batch summary 3,000 input and 300 output tokens via the Batch API, 1,000,000 calls a month |
$0.000225 | $0.000825 | $600.00 |
Monthly difference is gemini-2.5-flash minus claude-haiku-5-5. Batch rows use each provider's Batch API rates where published. Price both on your own workload.
Rates
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| anthropic/claude-haiku-5-5 | $0.10 | $0.50 | $0.01 | $0.125 | 1M |
| google/gemini-2.5-flash | $0.30 | $2.50 | $0.03 | — | 1M |
Price is one input. Before switching, run your own prompts through both and compare quality; then veqen diff prices the change at your production volume.