API Doc-CometAPI
HomeDashBoardModel_Price
HomeDashBoardModel_Price
Discord_Support
  1. veo3
  • GET START
    • Model New Release Announcement
    • Platform notification
    • Help Center
    • Quick Start
    • About Pricing
    • About Grouping
    • Interface Stability
    • Privacy policy
    • Terms of service
    • Error code description
    • Code example
    • Must see for use
    • Common Misconceptions
    • Confusion about use
    • Best Practices
      • CometAPI Account Balance Query API Usage Instructions
      • Retry Logic Documentation for CometAPI and OpenAI Official API
      • Midjourney Best Practices
      • Runway Best Practices
  • OpenAI Compatiable Endpoint
    • gpt-4o-image generates image
    • Chat
    • Recognizing Images
    • Models
    • Embeddings
    • Images
    • Realtime
    • Image Editing (gpt-image-1)
    • response
  • Audio
    • Create speech
    • Create transcription
    • Create translation
  • Anthropic Compatiable Endpoint
    • Anthropic Claude
  • Music Generation Endpoint
    • Suno
      • Setting suno Version
      • Generate lyrics
      • Generate music clip
      • Upload clip
      • Submit concatenation
      • Single task query
      • Batch query tasks
    • Udio(Temporarily unavailable)
      • Generate music
      • Task query
    • test
      • Suno
        • Full Track Audio Separation
        • Single Track Audio Separation
        • Create New Persona
        • Generate mp4 mv video
        • Get wav format file
        • Timing: lyrics, audio timeline
        • Create music using persona_id
  • Image Generation Endpoint
    • Midjourney(images)
      • Quick Tutorial - Complete Process in One Go
      • Task Fetching API
        • List by Condition
        • Fetch Single Task (most recommended)
      • Imagine
      • Submit Video
      • Action (UPSCALE; VARIATION; REROLL; ZOOM, etc.)
      • Blend (image -> image)
      • Describe (image -> text)
      • Modal (Area Redesign & Zoom)
    • Ideogram(images)
      • Official documentation (updated in real time)
      • Generate 3.0 (text to image)
      • Remix 3.0 (hybrid image)
      • Reframe 3.0(Reconstruction)
      • Replace Background 3.0(Background replacement)
      • Edit 3.0(Editing images)
      • ideogram Text Raw Image
      • ideogram Hybrid image
      • ideogram enlargement HD
      • ideogram describes the image
      • ideogram Edit image((legacy))
    • Flux(images)
      • Generate image (replicate format)
      • flux fine-tune images(Temporarily unavailable)
      • flux generate image(Temporarily unavailable)
      • flux query
    • Replicate(image)
      • replicate Generate
      • replicate query
    • Recraft(images)
      • Appendix
      • Recraft Generate Image
      • Recraft Vectorize Image
      • Recraft Remove Background
      • Recraft Clarity Upscale
      • Recraft Create style
      • Recraft Generative Upscale
  • Video Generation Ednpoint
    • veo3
      • veo3
        POST
    • runway(video)
      • official format
        • runway images raw video
        • runway to get task details
      • Reverse Format
        • generate(text)
        • generate(Reference images)
        • Video to Video Style Redraw
        • Act-one Expression Migration
        • feed-get task
    • kling (video)
      • callback_url
      • Expanded
      • Generating images
      • Text Generation Video
      • Image Generation Video
      • Video Extension
      • virtual try-on
      • lip sync
      • effects
      • Individual queries (videos)
    • MiniMax Conch(video)
      • MiniMax Conch Official Documentation
      • MiniMax Conch Generation
      • MiniMax Conch Query
      • MiniMax Conch Download
    • luma (video)
      • Official api interface format
        • luma generate
        • luma search
    • PIKA(video)
      • pika feed
      • PIKA Reference Video Generation
      • PIKA Reference Image Generation
      • PIKA reference text generation
    • sora
      • Reverse Format
        • Create Video
        • Query Video Task
        • Create Video
  • Software Integration Guide
    • cometapi Site API Call Testing
    • OpenManus
    • Chatbox
    • CherryStudio
    • Cursor
    • ChatHub
    • COZE
    • FastGPT
    • cline
    • dify
    • gptme
    • Immersive Translation
    • Lobe-Chat
    • Zotero
    • LangChain
    • AnythingLLM
    • Eudic Translation
    • OpenAI Translator
    • ChatAll Translation
    • Pot Translation
    • GPT Academic Optimization (gpt_academic)
    • NEXT CHAT (ChatGPT Next Web)
    • Obsidian's Text Generator Plugin
    • Open WebUI
    • avante.nvim
    • librechat
    • Lazy Customer Service
    • utools-ChatGPT Friend
    • IntelliJ Translation Plugin
    • n8n
  1. veo3

veo3

POST
https://api.cometapi.com/v1/chat/completions
Maintainer:Not configured
🌟 Notes on using veo3 for graph generation:
Since this interface is a technically realized interface, it may be slightly unstable

Request

Header Params
Authorization
string 
required
Example:
{{api-key}}
Body Params application/json
model
string 
required
The ID of the model to use. For details on which models are suitable for the chat API, see the model endpoint compatibility table: https://platform.openai.com/docs/models/model-endpoint-compatibility
messages
array [object {2}] 
required
Messages that generate the chat completion in chat format: https://platform.openai.com/docs/guides/text?api-mode=chat
role
string 
optional
content
string 
optional
stream
boolean 
optional
If set, partial message deltas will be sent, as in ChatGPT. Tokens will be sent as data-only server-sent events when they become available, and the stream is terminated by the message data: [DONE]. See the OpenAI Cookbook for sample code.
temperature
integer 
optional
Sampling temperature to use, between 0 and 2. Higher values (e.g., 0.8) make the output more random, while lower values (e.g., 0.2) make it more focused and deterministic. We generally recommend altering this or top_p but not both.
top_p
integer 
optional
An alternative to sampling with temperature, called nucleus sampling, where the model considers the tokens with top_p probability mass. So 0.1 means only tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.
n
integer 
optional
How many chat completion choices to generate for each input message.
stop
string 
optional
Up to 4 sequences where the API will stop generating further tokens.
max_tokens
integer 
optional
The maximum number of tokens to generate in the chat completion. The total length of input tokens and generated tokens is limited by the model’s context length.
presence_penalty
number 
optional
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they have appeared in the text so far, increasing the likelihood that the model will talk about new topics. See more about frequency and presence penalties: https://platform.openai.com/docs/api-reference/parameter-details
frequency_penalty
number 
optional
Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they have appeared in the text so far, increasing the likelihood that the model will talk about new topics. See more about frequency and presence penalties: https://platform.openai.com/docs/api-reference/parameter-details
logit_bias
null 
optional
Modifies the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value between -100 and 100. Mathematically, the bias is added to the logits generated by the model before sampling. The exact effect varies by model, but values between -1 and 1 should decrease or increase the likelihood of selection, while values like -100 or 100 should result in banning or exclusivity of the relevant tokens.
user
string 
optional
A unique identifier representing your end user, which can help OpenAI monitor and detect abuse. Learn more: https://platform.openai.com/docs/guides/safety-best-practices/end-user-ids
Examples
{
    "model": "veo3-pro",
    "stream": true,
    "messages": [
        {
            "role": "user",
            "content": "Generate a cute kitten sitting on a cloud, cartoon style"
        }
    ]
}

Request samples

Shell
JavaScript
Java
Swift
Go
PHP
Python
HTTP
C
C#
Objective-C
Ruby
OCaml
Dart
R
Request Request Example
Shell
JavaScript
Java
Swift
cURL
curl --location --request POST 'https://api.cometapi.com/v1/chat/completions' \
--header 'Authorization: {{api-key}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "veo3-pro",
    "stream": true,
    "messages": [
        {
            "role": "user",
            "content": "Generate a cute kitten sitting on a cloud, cartoon style"
        }
    ]
}'

Responses

🟢200Successful Response
application/json
Body
id
string 
required
The unique identifier for this chat completion.
object
string 
required
Object type
created
integer 
required
Unix timestamp when the chat completion was created
model
string 
required
Specific model name.
system_fingerprint
string 
required
Fingerprint representing the backend configuration used when the model was run.
choices
array [object {3}] 
required
A list containing the chat completion result options. If the n parameter in the request is greater than 1, there may be multiple options here.
index
integer 
optional
The index of this option in the list, starting from 0.
message
object 
optional
The message object generated by the model.
finish_reason
string 
optional
The reason the model stopped generating tokens.
usage
object 
required
Token usage statistics for this request.
completion_tokens
integer 
required
Number of tokens in the completion generated by the model.
completion_tokens_details
object 
required
More detailed information about the tokens in the model-generated content
prompt_tokens
integer 
required
Number of tokens in the input prompt.
prompt_tokens_details
object 
required
More detailed information about the tokens in the input prompt.
total_tokens
integer 
required
Total number of tokens used for this request
Example


> Video generation task created
> Task ID: `veo3: 16240615-a563-4d26-819d-a8559ce7d524`
> To prevent task interruption, you can continuously track progress from the following links:
> [Data Preview
](https: //asyncdata.net/web/veo3:16240615-a563-4d26-819d-a8559ce7d524) | [Source Data](https://asyncdata.net/source/veo3:16240615-a563-4d26-819d-a8559ce7d524)
> Waiting for processing.

> 🤔 Analyzing if prompt needs enhancement

> Type: Text-to-video generation
> 🎬 Starting video generation.......................................

> ✅ Preview video generated
> [📺 Online Preview
](https: //filesystem.site/cdn/20250620/b6dn4mQpz27ZHZBvh9u95N9G12ya0n.mp4) | [⏬ Download Video](https://filesystem.site/cdn/download/20250620/b6dn4mQpz27ZHZBvh9u95N9G12ya0n.mp4)

> 🔄 Optimizing video quality..................................

> 🎉 High-quality video generated

[▶️ Watch Online
](https: //filesystem.site/cdn/20250620/kGNathDwlJBJKy0uRc0HyfUWWvyGVr.mp4) | [⏬ Download Video](https://filesystem.site/cdn/download/20250620/kGNathDwlJBJKy0uRc0HyfUWWvyGVr.mp4)
Previous
Recraft Generative Upscale
Next
runway images raw video
Built with