Gemini 2.5 Flash
Fast, cheap and multimodal — the default high-volume Gemini.
Input / 1M
$0.3
Google
Output / 1M
$2.50
Cached input
$0.03
discounted reads
Context
1.0M
66K max output
Price history
input +100.0% · verified 2h agoPrice changes
6 changes| Date | Field | From | To | Change | Source |
|---|---|---|---|---|---|
| 2h ago | Cached input | $0.075 | $0.03 | -60.0% | openrouter |
| 2026-09-13 | Cached input | — | $0.075 | — | seed |
| 2025-06-17 | Input | $0.15 | $0.3 | +100.0% | historical-reference |
| 2025-06-17 | Output | $0.6 | $2.50 | +316.7% | historical-reference |
| 2025-04-17 | Input | — | $0.15 | — | historical-reference |
| 2025-04-17 | Output | — | $0.6 | — | historical-reference |
Specifications
- Provider
- Model ID
- gemini-2-5-flash
- Modality
- text+image+audio+video
- Context window
- 1.0M tokens
- Max output
- 66K tokens
- Tokenizer family
- gemini
Cost at similar prices
10,000 requests/month · 2000 in / 600 out tokens
- Gemini 2.5 Flash$21.00
- DeepSeek V3.2DeepSeek$7.86
- GPT-5 miniOpenAI$17.00
- GPT-5.1 miniOpenAI$17.00
- babbage-002OpenAI$10.40
- GPT-4.1 miniOpenAI$17.60
- Mistral Medium 3.1Mistral AI$20.00