claude-haiku-4-5 vs gemini-2.5-flash
Same spec sheet, same units: prices per 1M tokens, updated 2026-11-20.
Verdict: gemini-2.5-flash is 50% cheaper on output tokens ($2.5 vs $5 per 1M). Check the context and cached-input rows before deciding on price alone.
| claude-haiku-4-5 | gemini-2.5-flash | |
|---|---|---|
| Model ID | claude-haiku-4-5 | gemini-2.5-flash |
| Provider | anthropic | vertex_ai-language-models |
| Input /1M | $1 | $0.3 |
| Output /1M | $5 | $2.5 |
| Cached input /1M | $0.1 | $0.03 |
| Context | 200,000 | 1,048,576 |
| Max output | 64,000 | 65,536 |