Skip to content

fal.ai · Text to video

PixVerse V5.6

PixVerse V5.6, text to video, served by fal.ai. The OpenAPI schema for the fal-ai/pixverse/v5.6/text-to-video queue. Price: 5 s without audio: $0.35 at 360p/540p, $0.45 at 720p, $0.75 at 1080p; audio adds $0.45 (360p to 720p) or $0.75 (1080p); 8 s costs 2x and 10 s 2.2x the 5 s price (1080p not available at 10 s); the audio surcharge is scaled with the duration factor too, as the page does not say otherwise. Asynchronous: returns a request_id; poll fal/status and fetch fal/result with model "fal-ai/pixverse".

Usage based fal.aiVideofal/pixverse-5-6-text-to-videoListed

Activation pending; your agent will see it as unavailable until then.

Use this tool with your agent

Give this to your agent
Use my connected Agentik MCP server. I want to use the tool fal/pixverse-5-6-text-to-video (PixVerse V5.6, text to video). Call inspect_tool with {"tool_id": "fal/pixverse-5-6-text-to-video"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/pixverse-5-6-text-to-video" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.
Show the prompt

Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.

Parameters

NameTypeRequiredDescription
generate_audio_switchbooleanNoEnable audio generation (BGM, SFX, dialogue)
promptstringYesText prompt for the video generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
thinking_typestringNoPrompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision Options: enabled, disabled, auto.
seedintegerNo The same seed and the same prompt given to the same version of the model will output the same video every time.
durationstringNoThe duration of the generated video in seconds. 1080p videos are limited to 5 or 8 seconds Options: 5, 8, 10.
negative_promptstringNoNegative prompt to be used for the generation. Limited to 2048 UTF-8 encoded bytes. Because the limit counts bytes rather than characters, emoji and non-Latin or accented characters (which use multiple bytes each) can push a visually short prompt over the cap.
resolutionstringNoThe resolution of the generated video Options: 360p, 540p, 720p, 1080p.
stylestringNoThe style of the generated video Options: anime, 3d_animation, clay, comic, cyberpunk.
aspect_ratiostringNoThe aspect ratio of the generated video Options: 16:9, 4:3, 1:1, 3:4, 9:16.

How your agent calls it

First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:

{
  "tool_id": "fal/pixverse-5-6-text-to-video",
  "input": {
    "prompt": "a red cube slowly rotating on a white table, soft studio light",
    "resolution": "360p",
    "duration": "5"
  }
}

Price and billing

Price
Usage based
Model
Per call
Detail
The provider’s price, with no markup. Billed for measured usage.
  • The provider’s price, 0% markup.
  • One prepaid balance for every provider; your agent sees the price before it runs.
  • Pay for measured usage; unused reservations are released.