Gemini Omni 1.2 Flash Reference to Video Pricing
Turn reference images into consistent AI video with audio.
Estimate your cost
Pick what one request looks like. You pay only for what you run: no minimums, no commitments.
Starts at a 5 s clip at 720p from one reference image, a typical request: change any number to match yours.
Estimated cost
$0.3744
per request
- 1,200 input tokens at $1.5873015873 per million
- $0.001905
- 28,960 video output tokens at $12.6984126984 per million
- $0.3677
- 500 text output tokens at $9.5238095238 per million
- $0.004762
View pricing plans
Need more credits? Buy credits
Rates
What each option costs, as billed.
| Token Type | Price |
|---|---|
| Input tokens | $1.5873015873 per million tokens |
| Video output tokens | $12.6984126984 per million tokens |
| Text output tokens | $9.5238095238 per million tokens |
Output video uses a fixed number of tokens per second, set by resolution: about $0.025 per second at 360p, $0.074 at 720p, $0.11 at 1080p and $0.22 at 4K. Reference images and text output tokens, including thinking, are billed on top.