# POST /v1/chat/completions

**Method**: `POST`
**Endpoint**: `/v1/chat/completions`

This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
This section contains endpoint-specific behavior, parameters, or usage notes for this API.
For moderation, the official review covers at least three stages or directions:
1. Whether the submitted image contains a real person, or something too close to a real person.
2. Whether the prompt violates policy, such as violence, sexual content, copyright issues, or living celebrities.
3. Whether the generated result passes review. This is also why generation can fail after reaching more than 90% progress.

## Request Parameters

### Header Parameters

```text
Content-Type
string
Required
Example:
application/json
Accept
string
Required
Example:
application/json
Authorization
string
Optional
Default Value:
Bearer {{YOUR_API_KEY}}
```

### Body Parameters application/json

```text
model
string
Required
messages
array
[object]
Required
in
the chat format
to generate a chat completion message.
role
string
Optional
content
string
Optional
stream
boolean
Optional
If set, partial message deltas are streamed just like in ChatGPT. Tokens are sent as data-only
server-sent events
data: [DONE]
events as they become available, and the stream is terminated by a final message.
For sample code
, see the OpenAI Cookbook.
Example
{
"model"
:
"sora_video2"
,
"stream"
:
false
,
"messages"
:
[
{
"role"
:
"user"
,
"content"
:
[
{
"type"
:
"text"
,
"text"
:
  // provider-specific example normalized for English documentation
}
,
{
"type"
:
"image_url"
,
"image_url"
:
{
"url"
:
"https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
}
}
]
}
]
}
```

## Example Request

### Shell

```bash
curl --location --request POST '/v1/chat/completions' \
--header 'Accept: application/json' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "sora_video2",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
  // provider-specific example normalized for English documentation
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
                    }
                }
            ]
        }
    ]
}'
```

## Response

### 🟢 200 OK

**Content Type**: `application/json`

#### Response Schema

```text
id
string
Required
object
string
Required
created
integer
Required
choices
array
[object]
Required
index
integer
Optional
message
object
Optional
finish_reason
string
Optional
usage
object
Required
prompt_tokens
integer
Required
completion_tokens
integer
Required
total_tokens
integer
Required
```

#### Example

```json
{
    "id": "chatcmpl-123",
    "object": "chat.completion",
    "created": 1677652288,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "✅ Video GenerationSuccess，[click here](https:// provider-specific note
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 9,
        "completion_tokens": 12,
        "total_tokens": 21
    }
}
```