gpt-5-mini vs gemini-2.5-flash
Same spec sheet, same units: prices per 1M tokens, updated 2026-11-20.
Verdict: gpt-5-mini is 20% cheaper on output tokens ($2 vs $2.5 per 1M). Check the context and cached-input rows before deciding on price alone.
| gpt-5-mini | gemini-2.5-flash | |
|---|---|---|
| Model ID | gpt-5-mini | gemini-2.5-flash |
| Provider | openai | vertex_ai-language-models |
| Input /1M | $0.25 | $0.3 |
| Output /1M | $2 | $2.5 |
| Cached input /1M | $0.025 | $0.03 |
| Context | 272,000 | 1,048,576 |
| Max output | 128,000 | 65,536 |