veo3-chat format

POST

https://api.cometapi.com/v1/chat/completions

Maintainer:Not configured

🌟 Notes on using veo3 for videos generation:

Since this interface is a technically realized interface, it may be slightly unstable

Request

Header Params

Authorization

string

required

Example:

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.

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

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

Text-to-videourl image to video

{
    "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

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

cURL

Text-to-videourl image to video

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

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)

Task query

Submit video generation task