### Start DB-GPT Web Server

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-db-gpt

Launch the DB-GPT web server on the specified port.

```bash
dbgpt start webserver --port 5670
```

--------------------------------

### Install DB-GPT and OpenAI Python Packages

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-db-gpt

Install the necessary Python packages for DB-GPT and OpenAI integration.

```bash
pip install "dbgpt>=0.6.3rc2" openai
```

--------------------------------

### Python SDK Example

Source: https://docs.anyfast.ai/guides/model-api/anthropic/claude-sonnet-4

Example of how to use the OpenAI Python SDK to interact with the Claude Sonnet 4 API.

```APIDOC
## Python SDK Request Example

This example shows how to use the OpenAI Python SDK with Anyfast to access Claude Sonnet 4.

### Method
client.chat.completions.create

### Parameters
- `model` (string): `claude-sonnet-4-20250514`
- `messages` (array): List of message objects.

### Request Body Example
```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[
        {"role": "user", "content": "Write a Python function to merge two sorted arrays."}
    ]
)

print(response.choices[0].message.content)
```
```

--------------------------------

### Set Up DB-GPT Virtual Environment and Dependencies

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-db-gpt

Create a dedicated Conda environment for DB-GPT and install its dependencies, including proxy support.

```bash
conda create -n dbgpt_env python=3.10
conda activate dbgpt_env
pip install -e ".[proxy]"
```

--------------------------------

### Start MindSearch Frontend with Gradio

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-mindsearch

This command starts the Gradio-based frontend for MindSearch.

```bash
python frontend/mindsearch_gradio.py
```

--------------------------------

### Set Anyfast API Key and Start MindSearch Backend

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-mindsearch

Before starting the MindSearch backend, set your Anyfast API key as an environment variable. This command starts the MindSearch application with English language support, Anyfast model configuration, and DuckDuckGo search engine.

```bash
# Set your Anyfast API Key
export ANYFAST_API_KEY=<your-api-key>

# Start MindSearch
python -m mindsearch.app --lang en --model_format anyfast_config --search_engine DuckDuckGoSearch
```

--------------------------------

### Doubao Seedance 1.0 Lite I2V Example

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/doubao-seedance-1-0-lite-i2v-250428

An example of a request to the Doubao Seedance 1.0 Lite Image-to-Video API.

```yaml
openapi: 3.0.0
info:
  title: Doubao Seedance 1.0 Lite I2V API
  version: 1.0.0
paths:
  /v1/seedance/i2v:
    post:
      summary: Generate video from image
      operationId: generateVideoFromImage
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                prompt:
                  type: string
                  description: Text prompt for video generation
                  example: A majestic dragon flying over a castle
                negative_prompt:
                  type: string
                  description: Text prompt for elements to exclude from the video
                  example: ugly, deformed, blurry
                image_url:
                  type: string
                  description: URL of the input image
                  example: https://example.com/image.jpg
                seed:
                  type: integer
                  description: Seed for random number generation
                  example: 12345
                style_preset:
                  type: string
                  description: Style preset for video generation
                  example: cinematic
                resolution:
                  type: string
                  description: Resolution of the output video
                  example: 1024x1024
                num_frames:
                  type: integer
                  description: Number of frames in the output video
                  example: 25
                fps:
                  type: integer
                  description: Frames per second of the output video
                  example: 15
      responses:
        '200':
          description: Video generation successful
          content:
            application/json:
              schema:
                type: object
                properties:
                  id:
                    type: string
                    description: Unique identifier for the video generation task
                    example: task-12345
                  status:
                    type: string
                    description: Current status of the video generation task
                    example: processing
                  created_at:
                    type: integer
                    description: Timestamp when the task was created
                    example: 1773130665
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
```

--------------------------------

### OpenAPI Processing Example

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/doubao-seedance-1-5-pro-251215-i2v

An example demonstrating the processing endpoint within the OpenAPI specification.

```yaml
components:
  schemas:
    processing:
      type: object
      properties:
        created_at:
          type: integer
          example: 1773130665
      responses:
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
```

--------------------------------

### Processing Example

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/doubao-seedance-1-0-pro-fast-251015-i2v

This snippet shows an example of processing a request with the Doubao Seedance 1.0 Pro Fast model.

```APIDOC
## POST /v1/doubao-seedance-1.0-pro-fast

### Description
Processes a request using the Doubao Seedance 1.0 Pro Fast model.

### Method
POST

### Endpoint
/v1/doubao-seedance-1.0-pro-fast

### Request Body
- **prompt** (string) - Required - The input prompt for the model.
- **negative_prompt** (string) - Optional - A prompt to guide the model away from certain concepts.
- **style_raw** (string) - Optional - Specifies a raw style for the output.
- **aspect_ratio** (string) - Optional - The desired aspect ratio for the generated image.
- **num_inference_steps** (integer) - Optional - The number of inference steps to perform.
- **seed** (integer) - Optional - The seed for reproducibility.
- **guidance_scale** (number) - Optional - Controls how much the prompt influences the output.
- **controlnet_conditioning_scale** (number) - Optional - Scale for ControlNet conditioning.
- **controlnet_model** (string) - Optional - The ControlNet model to use.
- **controlnet_image** (string) - Optional - The ControlNet conditioning image.

### Response
#### Success Response (200)
- **code** (integer) - The status code of the operation.
- **msg** (string) - A message describing the result of the operation.
- **data** (object) - The data payload of the response.
  - **image** (string) - The generated image in base64 format.
  - **seed** (integer) - The seed used for generation.

#### Error Response
- **401** - Unauthorized
- **429** - Rate limit exceeded
```

--------------------------------

### Clone DB-GPT Repository

Source: https://docs.anyfast.ai/guides/usecases/use-anyfast-in-db-gpt

Clone the DB-GPT repository to your local machine to begin the setup process.

```bash
git clone https://github.com/eosphoros-ai/DB-GPT.git
cd DB-GPT
```

--------------------------------

### Example API Request

Source: https://docs.anyfast.ai/api-reference/introduction

This cURL command demonstrates how to make a chat completion request to the Anyfast API, including authentication and content type headers.

```bash
curl https://www.anyfast.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-3-5-sonnet-20241022",
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'
```

--------------------------------

### GPT-5.2 Chat Latest - Streaming Example

Source: https://docs.anyfast.ai/guides/model-api/openai/gpt-5-2-chat-latest

Demonstrates how to enable and receive real-time token streaming from the GPT-5.2 Chat Latest model using SSE.

```APIDOC
## POST /v1/responses (Streaming)

### Description
Sends a request to the GPT-5.2 Chat Latest model with streaming enabled to receive real-time token output.

### Method
POST

### Endpoint
/v1/responses

### Parameters
#### Request Body
- **model** (string) - Required - Must be `gpt-5.2-chat-latest`
- **input** (array) - Required - List of `{ role, content }` objects
- **stream** (boolean) - Required - Set to `true` to enable SSE streaming.
- **reasoning** (object) - Optional - `{ effort, summary }` — controls reasoning depth
- **text** (object) - Optional - `{ format, verbosity }` — controls output format and verbosity

### Request Example
```json
{
  "model": "gpt-5.2-chat-latest",
  "input": [
    { "role": "user", "content": "Write a short poem about the sea." }
  ],
  "stream": true
}
```

### Response
#### Success Response (200)
- **delta** (object) - Contains the streamed output tokens.

#### Response Example
```
[Streaming Server-Sent Events]
```
```

--------------------------------

### Chat Completions (Python SDK)

Source: https://docs.anyfast.ai/guides/model-api/alibaba/qwen2-vl-7b-instruct

Example of how to send a chat completion request to the Qwen2-VL-7B-Instruct model using the OpenAI Python SDK.

```APIDOC
## Chat Completions with OpenAI SDK

### Description
Utilizes the OpenAI-compatible API to interact with the Qwen2-VL-7B-Instruct model using the Python SDK.

### Method
Client.chat.completions.create

### Parameters
- **model**: `qwen2-vl-7b-instruct` (string, required)
- **messages**: List of message objects (list of dict, required)
- **stream**: Boolean, optional (defaults to `false`)

### Request Example
```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="qwen2-vl-7b-instruct",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```
```

--------------------------------

### Image to Video (Python)

Source: https://docs.anyfast.ai/guides/model-api/kuaishou/kling-v3-omni

Generate a video using a reference image as a guide. This Python example shows how to include an image URL in the request to influence the video generation, such as making a person wave.

```python
import requests

response = requests.post(
    "https://www.anyfast.ai/kling/v1/videos/omni-video",
    headers={
        "Authorization": "Bearer YOUR_API_KEY",
        "Content-Type": "application/json"
    },
    json={
        "model_name": "kling-v3-omni",
        "prompt": "Make the person in <<<image_1>>> wave to the camera",
        "image_list": [
            {"image_url": "https://example.com/photo.jpg"}
        ],
        "duration": "5",
        "mode": "pro",
        "aspect_ratio": "16:9"
    }
)

task = response.json()
print(f"Task ID: {task['task_id']}")
```

--------------------------------

### Python Chat Completion with Qwen3-Coder-Next

Source: https://docs.anyfast.ai/guides/model-api/alibaba/qwen3-coder-next

This Python snippet demonstrates how to use the OpenAI SDK with Anyfast's API to get a chat completion from Qwen3-Coder-Next. Ensure you have the 'openai' library installed and replace YOUR_API_KEY.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="qwen3-coder-next",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### Quick Example: Python Request for GPT-5.2

Source: https://docs.anyfast.ai/guides/model-api/openai/gpt-5-2

This Python script demonstrates how to interact with the GPT-5.2 model using the OpenAI client library. Configure your API key and base URL accordingly.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.responses.create(
    model="gpt-5.2",
    input=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ],
    reasoning={"effort": "high", "summary": "auto"},
    text={"format": {"type": "text"}, "verbosity": "medium"},
    store=True
)

print(response.output[0].content[0].text)
```

--------------------------------

### HappyHorse Task Query OpenAPI Specification

Source: https://docs.anyfast.ai/api-reference/model-api/alibaba/happyhorse-task-query

This OpenAPI specification defines the GET /v1/video/generations/{task_id} endpoint for querying the status and result of a HappyHorse video generation task. It includes request parameters, response schemas, and example values.

```yaml
openapi: 3.1.0
info:
  title: HappyHorse Task Query
  description: >-
    Query the status and result of a HappyHorse 1.0 video generation task via
    Anyfast API
  version: 1.0.0
servers:
  - url: https://www.anyfast.ai
security:
  - bearerAuth: []
paths:
  /v1/video/generations/{task_id}:
    get:
      summary: Query Video Generation Task
      description: >-
        Retrieve the status and result of a HappyHorse video generation task by
        its ID.
      operationId: getHappyhorseTaskStatus
      parameters:
        - name: task_id
          in: path
          required: true
          schema:
            type: string
          description: >-
            Task ID returned from the video generation request (format:
            `asyntask_xxx`).
          example: asyntask_jwgfhsG0m2aDjLmiiELRf74eoWmss6ya
      responses:
        '200':
          description: Task status retrieved
          content:
            application/json:
              schema:
                type: object
                properties:
                  code:
                    type: string
                    example: success
                  message:
                    type: string
                    example: ''
                  data:
                    type: object
                    properties:
                      task_id:
                        type: string
                        example: asyntask_jwgfhsG0m2aDjLmiiELRf74eoWmss6ya
                      action:
                        type: string
                        description: >-
                          Sub-type: `generate`, `firstTailGenerate`,
                          `referenceGenerate`, `omniGenerate`.
                        example: generate
                      status:
                        type: string
                        enum:
                          - NOT_START
                          - QUEUED
                          - IN_PROGRESS
                          - SUCCESS
                          - FAILURE
                        description: Task status.
                        example: SUCCESS
                      result_url:
                        type: string
                        description: >-
                          Pre-signed video download URL (valid 24 hours).
                          Omitted on failure.
                        example: >-
                          https://dashscope-a717.oss-accelerate.aliyuncs.com/.../xxx_refiner.mp4?Expires=...
                      fail_reason:
                        type: string
                        description: >-
                          On `status = SUCCESS`, copies `result_url` (backward
                          compat for legacy clients). On `status = FAILURE`,
                          contains the error message.
                        example: >-
                          https://dashscope-a717.oss-accelerate.aliyuncs.com/.../xxx_refiner.mp4?Expires=...
                      submit_time:
                        type: integer
                        example: 1777343862
                      start_time:
                        type: integer
                        description: Upstream start timestamp; `0` if not started yet.
                        example: 1777343866
                      finish_time:
                        type: integer
                        example: 1777343961
                      progress:
                        type: string
                        example: 100%
                      request_id:
                        type: string
                        example: 20260428023742441081000FMrSbjcs
                      data:
                        type: object
                        description: Upstream DashScope raw output and usage.
                        properties:
                          output:
                            type: object
                            properties:
                              task_id:
                                type: string
                                description: Upstream DashScope task ID.
                                example: e45a6a1b-6f05-43e5-ab06-ddfdc97587a7
                              task_status:
                                type: string
                                enum:
                                  - PENDING
                                  - RUNNING
                                  - SUCCEEDED
                                  - FAILED
                                  - CANCELED
                                  - UNKNOWN

```

--------------------------------

### Configure OpenAI SDK with Anyfast Base URL (Python)

Source: https://docs.anyfast.ai/api-reference/introduction

Initialize the OpenAI client with a custom base URL to direct requests to the Anyfast API.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)
```

--------------------------------

### Poll HappyHorse Task Status and Get Result (Python)

Source: https://docs.anyfast.ai/guides/model-api/alibaba/happyhorse-task-query

This Python script polls the status of a HappyHorse video generation task every 15 seconds. It prints the video URL if the task is successful or the failure reason if it fails. Ensure you have the 'requests' and 'time' libraries installed.

```python
import requests, time

task_id = "asyntask_jwgfhsG0m2aDjLmiiELRf74eoWmss6ya"
while True:
    r = requests.get(
        f"https://www.anyfast.ai/v1/video/generations/{task_id}",
        headers={"Authorization": "Bearer YOUR_API_KEY"}
    ).json()
    status = r["data"]["status"]
    if status == "SUCCESS":
        print("Video URL:", r["data"]["result_url"])
        break
    if status == "FAILURE":
        print("Failed:", r["data"]["fail_reason"])
        break
    time.sleep(15)
```

--------------------------------

### Streaming Chat Completions with Qwen2-VL-7B-Instruct in Python

Source: https://docs.anyfast.ai/guides/model-api/alibaba/qwen2-vl-7b-instruct

This Python example demonstrates how to receive streaming responses from the Qwen2-VL-7B-Instruct model using the OpenAI SDK. It iterates over the stream and prints each chunk of content as it arrives.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

stream = client.chat.completions.create(
    model="qwen2-vl-7b-instruct",
    messages=[
        {"role": "user", "content": "Write a short poem about the sea."}
    ],
    stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
```

--------------------------------

### Python OpenAI SDK for Qwen2.5-VL-7B-Instruct

Source: https://docs.anyfast.ai/guides/model-api/alibaba/qwen2.5-vl-7b-instruct

Integrate Qwen2.5-VL-7B-Instruct into your Python application using the OpenAI SDK. Set your API key and the base URL for Anyfast. This example shows a standard chat completion.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="qwen2.5-vl-7b-instruct",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### Python Chat Completions with OpenAI SDK

Source: https://docs.anyfast.ai/guides/model-api/alibaba/qwen3-32b

This Python snippet demonstrates how to use the OpenAI SDK to interact with the Qwen3-32B model through Anyfast. Configure the client with your API key and base URL, then create a chat completion.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="qwen3-32b",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### cURL Example

Source: https://docs.anyfast.ai/guides/model-api/anthropic/claude-sonnet-4

Example of how to send a request to the Claude Sonnet 4 API using cURL.

```APIDOC
## cURL Request Example

This example demonstrates how to call the Claude Sonnet 4 API using cURL.

### Method
POST

### Endpoint
https://www.anyfast.ai/v1/messages

### Request Body
```json
{
  "model": "claude-sonnet-4-20250514",
  "messages": [
    { "role": "user", "content": "Write a Python function to merge two sorted arrays." }
  ]
}
```
```

--------------------------------

### OpenAPI Specification Example

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/doubao-seedance-1-0-pro-250528-i2v

An example snippet from an OpenAPI specification, illustrating processing details and error codes.

```yaml
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

openapi: 3.0.0
info:
  title: Doubao Seedance 1.0 Pro 250528 i2v API
  version: 1.0.0
paths:
  /v1/seedance/i2v:
    post:
      summary: Generate video from image
      operationId: generateVideoFromImage
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                prompt:
                  type: string
                  description: Text prompt to guide video generation.
                  example: "A cat playing with a ball of yarn."
                negative_prompt:
                  type: string
                  description: Text prompt for elements to exclude from the video.
                  example: "blurry, low quality, text"
                image_url:
                  type: string
                  description: URL of the input image.
                  example: "https://example.com/image.jpg"
                num_frames:
                  type: integer
                  description: Number of frames in the generated video.
                  example: 16
                seed:
                  type: integer
                  description: Seed for reproducible generation.
                  example: 12345
      responses:
        '200':
          description: Video generation successful
          content:
            application/json:
              schema:
                type: object
                properties:
                  video_url:
                    type: string
                    description: URL of the generated video.
                    example: "https://example.com/video.mp4"
                  seed:
                    type: integer
                    description: Seed used for this generation.
                    example: 12345
        '400':
          description: Bad Request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded


```

--------------------------------

### Quick Example: cURL Request for GPT-5.2

Source: https://docs.anyfast.ai/guides/model-api/openai/gpt-5-2

Use this cURL command to make a request to the GPT-5.2 model via the Anyfast Responses API. Ensure you replace 'YOUR_API_KEY' with your actual API key.

```bash
curl https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.2",
    "input": [
      { "role": "user", "content": "Explain quantum entanglement in simple terms." }
    ],
    "reasoning": {
      "effort": "high",
      "summary": "auto"
    },
    "text": {
      "format": { "type": "text" },
      "verbosity": "medium"
    },
    "store": true
}'
```

--------------------------------

### Seedance Asset — Get Asset

Source: https://docs.anyfast.ai/llms.txt

Get a single asset detail by Id. This is a read-only operation and is not billed.

```APIDOC
## Seedance Asset — Get Asset

### Description
Get a single asset detail by Id. This is a read-only operation and is not billed.

### Method
GET

### Endpoint
/v1/bytedance/volc-asset/{asset_id}

### Parameters
#### Path Parameters
- **asset_id** (string) - Required - The ID of the asset to retrieve.

### Response
#### Success Response (200)
- **asset_id** (string) - The ID of the asset.
- **asset_type** (string) - The type of the asset (e.g., 'image', 'audio', 'video').
- **group_id** (string) - The ID of the asset group.
- **created_at** (string) - The timestamp when the asset was created.
- **asset_name** (string) - Optional - The custom name of the asset.
```

--------------------------------

### Configure OpenAI SDK with Anyfast Base URL (Node.js)

Source: https://docs.anyfast.ai/api-reference/introduction

Instantiate the OpenAI client with a custom baseURL to route requests to the Anyfast API.

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://www.anyfast.ai/v1",
});
```

--------------------------------

### API Response Example

Source: https://docs.anyfast.ai/guides/system-api/models-list

This is an example of the JSON response structure returned by the /v1/models endpoint, showing available models with their details.

```json
{
  "data": [
    {
      "id": "gpt-4o",
      "object": "model",
      "created": 1626777600,
      "owned_by": "openai",
      "supported_endpoint_types": ["openai"]
    },
    {
      "id": "claude-sonnet-4-5-20250929",
      "object": "model",
      "created": 1626777600,
      "owned_by": "vertex-ai",
      "supported_endpoint_types": ["openai", "anthropic"]
    }
  ]
}
```

--------------------------------

### Make First Chat API Call with Node.js

Source: https://docs.anyfast.ai/quickstart

This Node.js example shows how to use the OpenAI library to interact with a chat model through Anyfast. Remember to replace YOUR_API_KEY and configure your channels.

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://www.anyfast.ai/v1",
});

const response = await client.chat.completions.create({
  model: "claude-3-5-sonnet-20241022",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response.choices[0].message.content);
```

--------------------------------

### Python SDK Streaming Example

Source: https://docs.anyfast.ai/guides/model-api/anthropic/claude-sonnet-4

Example of how to use the OpenAI Python SDK for streaming responses from the Claude Sonnet 4 API.

```APIDOC
## Python SDK Streaming Example

This example demonstrates how to enable and receive streaming responses from Claude Sonnet 4 using the OpenAI Python SDK.

### Method
client.chat.completions.create (with `stream=True`)

### Parameters
- `model` (string): `claude-sonnet-4-20250514`
- `messages` (array): List of message objects.
- `stream` (boolean): Set to `True` to enable streaming.

### Request Body Example
```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

stream = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[
        {"role": "user", "content": "Explain the difference between async and sync programming."}
    ],
    stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")
```
```

--------------------------------

### Python Chat Completion with OpenAI SDK

Source: https://docs.anyfast.ai/guides/model-api/openai/gpt-5-pro

This Python snippet demonstrates how to use the OpenAI SDK to interact with GPT-5 Pro. Configure the client with your API key and the Anyfast base URL. Replace 'YOUR_API_KEY' with your actual API key.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-5-pro",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### OpenAPI Specification - Processing Example

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/doubao-seedance-1-0-pro-fast-251015-i2v

This snippet shows an example of the 'processing' status within the OpenAPI specification, including an integer timestamp.

```yaml
components:
  schemas:
    ProcessingResponse:
      type: object
      properties:
        processing_code:
          type: integer
          example: 200
        msg:
          type: string
          example: processing
        created_at:
          type: integer
          example: 1773130665
    ErrorResponse:
      type: object
      properties:
        error_code:
          type: integer
        msg:
          type: string
  responses:
    '401':
      description: Unauthorized
    '429':
      description: Rate limit exceeded
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
```

--------------------------------

### SSE Response Format Example

Source: https://docs.anyfast.ai/guides/model-api/google/gemini-2-5-flash-image-stream

Illustrates the structure of Server-Sent Events (SSE) responses for Gemini 2.5 Flash Image (Stream). It shows examples of thinking chunks, image data chunks, and final usage metadata chunks.

```json
data: {"candidates":[{"content":{"role":"model","parts":[{"text":"...","thought":true}]}}],"usageMetadata":{"trafficType":"ON_DEMAND"},"modelVersion":"gemini-2.5-flash-image","createTime":"...","responseId":"..."}

data: {"candidates":[{"content":{"role":"model","parts":[{"inlineData":{"mimeType":"image/png","data":"<base64>"}}]}}],...}

data: {"usageMetadata":{"promptTokenCount":8,"candidatesTokenCount":1120,"totalTokenCount":1392,"trafficType":"ON_DEMAND","promptTokensDetails":[{"modality":"TEXT","tokenCount":8}],"candidatesTokensDetails":[{"modality":"IMAGE","tokenCount":1120}],"thoughtsTokenCount":264}}
```

--------------------------------

### Python OpenAI SDK for GPT-5 Mini Chat Completions

Source: https://docs.anyfast.ai/guides/model-api/openai/gpt-5-mini

This Python script demonstrates how to use the OpenAI SDK to interact with GPT-5 Mini. Configure the client with your API key and the Anyfast base URL.

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[
        {"role": "user", "content": "Explain quantum entanglement in simple terms."}
    ]
)

print(response.choices[0].message.content)
```

--------------------------------

### Get Asset

Source: https://docs.anyfast.ai/api-reference/model-api/bytedance/volc-asset-get-asset

Retrieves the details of a specific asset using its unique identifier. This is a read-only operation.

```APIDOC
## POST /volc/asset/GetAsset

### Description
Get a single asset detail by Id. This is a read-only operation and is not billed.

### Method
POST

### Endpoint
/volc/asset/GetAsset

### Parameters
#### Request Body
- **Id** (string) - Required - Asset ID to query.

### Request Example
{
  "Id": "asset-20260528140922-d9646"
}

### Response
#### Success Response (200)
- **Id** (string)
- **Name** (string)
- **URL** (string) - Asset file URL.
- **AssetType** (string) - Enum: Image, Video, Audio
- **GroupId** (string)
- **Status** (string) - Enum: Active, Inactive
- **ProjectName** (string)
- **CreateTime** (string)
- **UpdateTime** (string)

#### Response Example
{
  "Id": "asset-20260528140922-d9646",
  "Name": "character-reference",
  "URL": "https://ark-media-asset.tos-cn-beijing.volces.com/...",
  "AssetType": "Video",
  "GroupId": "group-20260528140601-tp9hw",
  "Status": "Active",
  "ProjectName": "default",
  "CreateTime": "2026-05-28T06:09:22Z",
  "UpdateTime": "2026-05-28T06:09:31Z"
}
```