GeminiText to videoAvailable now
Geminigemini-omni-1.1-flash
gemini-omni-1.1-flash is a text to video tool from Gemini that runs in the background and returns video. Pay as you go from $0.00000195 per token, with one API key.
Try itfrom $0.00000195 / token
Pricing
About $1.545086 per run for a 10-second video, the maximum. $22.75 per 1M video output tokens, $11.70 per 1M text output tokens, $1.95 per 1M input tokens. The final charge comes from usage.
Limits
- Runs
- In the background
- Returns
- video
- Longest queue wait
- 3600s
- Run deadline
- 3600s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 16
Input
| Field | Kind | Default | Description |
|---|---|---|---|
input | JSON | — | The prompt: a text, or content parts (images, videos, then the text prompt). Existing contents input remains supported. |
contents | JSON | — | Required. The content of the current conversation with the model. For single-turn queries, this is a single instance. For multi-turn queries like [chat](https://ai.google.dev/gemini-api/docs/text-generation#chat), this is a repeated field that contains the conversation history and the latest request. |
response_format | JSON | — | |
generationConfig | JSON | — | Legacy generation settings: only the ones Interactions take are accepted, sent as generation_config (maxOutputTokens as max_output_tokens, seed, thinkingConfig.thinkingLevel as thinking_level). Prefer generation_config. |
generation_config | JSON | — | Configuration parameters for the model interaction. |
systemInstruction | JSON | — | Legacy system instruction, text parts only: the parts' text is joined with newlines and sent as system_instruction. Prefer system_instruction. |
system_instruction | text | — | System instruction for the interaction. |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "gemini",
"model": "gemini-omni-1.1-flash",
"input": {}
}'