Model specifications
- Context
- 131,072 tokens
- Maximum output
- 65,536 tokens
- Architecture
- text+image+video->text+video
- Tokenizer
- Gemini
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Video (with audio)
- $0.0338 per second
- 360p$0.0338
- 720p$0.1014
- 1080p$0.152
- 4K$0.3041
- Input
- $1.5 per 1M tokens
- Output
- $9 per 1M tokens
Model configuration
Reasoning
- Reasoning required
- Yes
- Default parameters
- low
- Capabilities
- high, low
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
This creates a video job. Poll its status before downloading the completed video.
curl --fail-with-body https://openrouter.ai/api/v1/videos \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"google/gemini-omni-1.1-flash","prompt":"A slow camera move across a sunlit mountain landscape"}'
# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/v1/videos/JOB_ID" \
-H "Authorization: Bearer $OPENROUTER_API_KEY"Input → Output
No · high · low
Supported API parameters
include_reasoningmax_tokensreasoningreasoning_effortseedtemperaturetop_p1 Provider
Checked: November 6, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
Google AI Studio
Not provided- Context
- 131K
- Maximum output
- 66K