Claude Haiku 4.5 vs Gemini 2.5 Flash
Data reconciled August 15, 2026
Short answer
Gemini 2.5 Flash is 3.3× cheaper than Claude Haiku 4.5 on input and 2× cheaper on output, while giving up nothing on context or capabilities. On measurable parameters the choice is unambiguous.
Side by side
| Parameter | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Provider | Anthropic | Google (Gemini) |
| Input, $ per 1M tokens | $1.00 | $0.30 |
| Output, $ per 1M tokens | $5.00 | $2.50 |
| Cache read, $ per 1M | $0.10 | $0.03 |
| Context window | 200,000 | 1,048,576 |
| Max output | 64,000 | 65,535 |
| Vision | yes | yes |
| Tools | yes | yes |
| Reasoning | yes | yes |
| Status | available | available |
What it costs on your own workload
A price gap per million tokens says little until your volumes are plugged in: on a long fixed system prompt the winner is the model with cheap cache reads, not the one with a cheap input rate. Run Claude Haiku 4.5 and Gemini 2.5 Flash against your own numbers.
Open the cost calculatorWhat is deliberately absent
We do not compare answer quality and we do not reprint third-party benchmarks. We have no quality measurements of our own, and external tables go stale faster than prices while being compiled, almost always, by someone with a stake in the result. What is here is only what we reconcile ourselves every day: prices, limits and supported capabilities.