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-4-5gemini-2.5-flash
Model IDclaude-haiku-4-5gemini-2.5-flash
Provideranthropicvertex_ai-language-models
Input /1M$1$0.3
Output /1M$5$2.5
Cached input /1M$0.1$0.03
Context200,0001,048,576
Max output64,00065,536

claude-haiku-4-5 details · gemini-2.5-flash details