### Minimal Python Example

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/CHANGELOG.md

A basic example demonstrating how to interact with the API using Python.

```python
import os
import openai

openai.api_key = os.getenv("AGNES_API_KEY")

completion = openai.ChatCompletion.create(
  model="agnes-2.0-flash",
  messages=[
    {"role": "user", "content": "Hello Agnes!"}
  ]
)

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

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

### Minimal Curl Example

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/CHANGELOG.md

A basic example demonstrating how to interact with the API using curl.

```bash
curl -X POST \
  'https://api.agnesai.com/v1/chat/completions' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -d '{ 
    "model": "agnes-2.0-flash", 
    "messages": [{"role": "user", "content": "Hello Agnes!"}]
  }'
```

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

### Minimal Node.js Example

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/CHANGELOG.md

A basic example demonstrating how to interact with the API using Node.js.

```javascript
import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.AGNES_API_KEY,
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "agnes-2.0-flash",
    messages: [
      {"role": "user", "content": "Hello Agnes!"},
    ],
  });

  console.log(completion.choices[0].message.content);
}

main();
```

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

### Query Video Results by Video ID

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/docs/FAQ.md

Use this GET request to retrieve video results using the returned video_id. Do not use task_id for current video result polling unless specifically documented.

```text
GET https://apihub.agnes-ai.com/agnesapi?video_id=<VIDEO_ID>
```

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

### Video Generation API Request

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Initiate a video generation task using this cURL command. Video generation is asynchronous; you will receive a `video_id` to poll for results. Ensure your API key is correctly configured.

```bash
curl -X POST https://apihub.agnes-ai.com/v1/videos \
  -H "Authorization: Bearer $AGNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-video-v2.0",
    "prompt": "A cinematic shot of a cat walking on the beach at sunset, soft ocean waves, warm golden lighting, realistic motion",
    "height": 768,
    "width": 1152,
    "num_frames": 121,
    "frame_rate": 24
  }'
```

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

### Video Generation

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Generate videos from text prompts. This is an asynchronous process that requires creating a task and then polling for the result.

```APIDOC
## POST /v1/videos

### Description
Initiates a video generation task based on the provided prompt and parameters. Video generation is asynchronous.

### Method
POST

### Endpoint
https://apihub.agnes-ai.com/v1/videos

### Parameters
#### Request Body
- **model** (string) - Required - The video generation model to use (e.g., "agnes-video-v2.0").
- **prompt** (string) - Required - A detailed description of the video to generate.
- **height** (integer) - Required - The height of the generated video in pixels.
- **width** (integer) - Required - The width of the generated video in pixels.
- **num_frames** (integer) - Required - The total number of frames for the video.
- **frame_rate** (integer) - Required - The frame rate of the generated video.

### Request Example
```json
{
  "model": "agnes-video-v2.0",
  "prompt": "A cinematic shot of a cat walking on the beach at sunset, soft ocean waves, warm golden lighting, realistic motion",
  "height": 768,
  "width": 1152,
  "num_frames": 121,
  "frame_rate": 24
}
```

### Response
#### Success Response (200)
- **video_id** (string) - A unique identifier for the video generation task.

#### Response Example
```json
{
  "video_id": "vid_abc123xyz789"
}
```

## GET /agnesapi?video_id=<VIDEO_ID>

### Description
Polls for the result of a video generation task using the `video_id`.

### Method
GET

### Endpoint
https://apihub.agnes-ai.com/agnesapi?video_id=<VIDEO_ID>

### Parameters
#### Query Parameters
- **video_id** (string) - Required - The ID of the video generation task to query.

### Response
#### Success Response (200)
- **status** (string) - The status of the video generation task (e.g., "processing", "completed", "failed").
- **url** (string) - The URL of the generated video if the status is "completed".

#### Response Example
```json
{
  "status": "completed",
  "url": "https://apihub.agnes-ai.com/videos/generated/video1.mp4"
}
```
```

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

### Set AGNES_API_KEY Environment Variable

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Use this command to set your API key as an environment variable for local development. Replace 'your_api_key_here' with your actual key.

```bash
export AGNES_API_KEY="your_api_key_here"
```

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

### Chat Completions

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Generate chat completions by sending a prompt to the chat API. Supports streaming for real-time responses.

```APIDOC
## POST /v1/chat/completions

### Description
Generates a chat completion response based on the provided messages and model.

### Method
POST

### Endpoint
https://apihub.agnes-ai.com/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for chat completions (e.g., "agnes-2.0-flash").
- **messages** (array) - Required - An array of message objects, each with a `role` (user, system, assistant) and `content`.
- **stream** (boolean) - Optional - Whether to stream the response. Defaults to false.

### Request Example
```json
{
  "model": "agnes-2.0-flash",
  "messages": [
    {
      "role": "user",
      "content": "Explain how to integrate an OpenAI-compatible API gateway."
    }
  ],
  "stream": true
}
```

### Response
#### Success Response (200)
- **content** (string) - The generated chat response.
- **role** (string) - The role of the message sender (e.g., "assistant").

#### Response Example
```json
{
  "model": "agnes-2.0-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "To integrate an OpenAI-compatible API gateway..."
      },
      "finish_reason": "stop"
    }
  ]
}
```
```

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

### Chat Completions API

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

Use the chat completions endpoint for both `agnes-1.5-flash` and `agnes-2.0-flash` models. `agnes-1.5-flash` is recommended for high-throughput, low-latency tasks, while `agnes-2.0-flash` supports advanced features like tool calling, coding, reasoning, and multimodal input.

```APIDOC
## POST /v1/chat/completions

### Description
Provides chat completions and text generation capabilities. Supports image URL input for multimodal tasks with `agnes-2.0-flash`.

### Method
POST

### Endpoint
https://apihub.agnes-ai.com/v1/chat/completions

### Parameters
#### Request Body
- **model** (string) - Required - The model to use for chat completions (e.g., `agnes-1.5-flash`, `agnes-2.0-flash`).
- **messages** (array) - Required - A list of messages comprising the conversation.
- **stream** (boolean) - Optional - Whether to stream back partial message deltas as they are generated.
- **tools** (array) - Optional - A list of tools the model may call.
- **tool_choice** (string or object) - Optional - Controls how the tools are called.

### Request Example
```json
{
  "model": "agnes-2.0-flash",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who won the world series in 2020?", "image_url": "https://example.com/image.jpg"} 
  ],
  "stream": true
}
```

### Response
#### Success Response (200)
- **id** (string) - Unique identifier for the response.
- **choices** (array) - A list of generated message choices.
- **usage** (object) - Usage statistics for the request.

#### Response Example
```json
{
  "id": "chatcmpl-123",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "The Los Angeles Dodgers won the World Series in 2020."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 20,
    "total_tokens": 30
  }
}
```
```

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

### Legacy Video Task Query

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

This is a legacy format for querying video task results using task_id. It is recommended to use video_id for current integrations.

```text
GET https://apihub.agnes-ai.com/v1/videos/{task_id}
```

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

### OpenAI-Compatible Chat Completions Endpoint

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/docs/FAQ.md

Agnes AI supports OpenAI-compatible integrations. Use this endpoint for chat workflows.

```text
POST /v1/chat/completions
```

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

### Image Generation API Request

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Send a request to the Agnes AI API to generate an image. Replace "$AGNES_API_KEY" with your actual API key or ensure it's set as an environment variable. The "size" parameter specifies the output resolution.

```bash
curl https://apihub.agnes-ai.com/v1/images/generations \
  -H "Authorization: Bearer $AGNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-image-2.1-flash",
    "prompt": "A luminous floating city above a misty canyon at sunrise, cinematic realism",
    "size": "1024x768"
  }'
```

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

### Image Generations

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Create images from text prompts using the image generation API.

```APIDOC
## POST /v1/images/generations

### Description
Generates an image based on the provided text prompt and model.

### Method
POST

### Endpoint
https://apihub.agnes-ai.com/v1/images/generations

### Parameters
#### Request Body
- **model** (string) - Required - The image generation model to use (e.g., "agnes-image-2.1-flash").
- **prompt** (string) - Required - A detailed description of the image to generate.
- **size** (string) - Optional - The desired size of the generated image (e.g., "1024x768").

### Request Example
```json
{
  "model": "agnes-image-2.1-flash",
  "prompt": "A luminous floating city above a misty canyon at sunrise, cinematic realism",
  "size": "1024x768"
}
```

### Response
#### Success Response (200)
- **url** (string) - The URL of the generated image.

#### Response Example
```json
{
  "created": 1678887000,
  "data": [
    {
      "url": "https://apihub.agnes-ai.com/images/generated/image1.png"
    }
  ]
}
```
```

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

### Video Generation

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

Generates videos from text, images, or multiple images. Supports keyframe animation and asynchronous generation. Use the returned video_id to poll for results.

```APIDOC
## POST /v1/videos

### Description
Generates videos based on text or image inputs. Supports multi-image video and keyframe animation. Generation is asynchronous.

### Method
POST

### Endpoint
/v1/videos

### Parameters
#### Request Body
- **prompt** (string) - Required - The text prompt to guide video generation.
- **image_inputs** (array) - Optional - An array of images for image-to-video or multi-image video generation.
- **keyframes** (array) - Optional - Keyframe data for animation control.

### Request Example
```json
{
  "prompt": "A robot walking through a forest",
  "image_inputs": ["url1", "url2"]
}
```

### Response
#### Success Response (200)
- **video_id** (string) - The ID to poll for video generation results.

#### Response Example
```json
{
  "video_id": "v_abc123xyz"
}
```
```

```APIDOC
## GET /agnesapi?video_id=<VIDEO_ID>

### Description
Polls for the results of a video generation task using the provided `video_id`.

### Method
GET

### Endpoint
/agnesapi

### Parameters
#### Query Parameters
- **video_id** (string) - Required - The ID of the video generation task.

### Response
#### Success Response (200)
- **status** (string) - The current status of the video generation (e.g., 'processing', 'completed', 'failed').
- **video_url** (string) - The URL of the generated video if status is 'completed'.

#### Response Example
```json
{
  "status": "completed",
  "video_url": "https://example.com/video.mp4"
}
```
```

```APIDOC
## GET /v1/videos/{task_id}

### Description
Legacy endpoint to query video results using a `task_id`. It is recommended to use `video_id` for current integrations.

### Method
GET

### Endpoint
/v1/videos/{task_id}

### Parameters
#### Path Parameters
- **task_id** (string) - Required - The ID of the video generation task (legacy).

### Response
#### Success Response (200)
- **status** (string) - The current status of the video generation.
- **video_url** (string) - The URL of the generated video if available.

#### Response Example
```json
{
  "status": "completed",
  "video_url": "https://example.com/legacy_video.mp4"
}
```
```

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

### Agnes AI API Configuration

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

Configure your client or tool to use Agnes AI by setting the Base URL and API Key. The chat endpoint is also specified for compatibility.

```text
Base URL: https://apihub.agnes-ai.com/v1
API Key: YOUR_API_KEY
Chat endpoint: /v1/chat/completions
```

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

### Authentication Header

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

Include this header in your API requests for authentication.

```text
Authorization: Bearer YOUR_API_KEY
```

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

### Retry on Upstream Processing Timeout Error (524)

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/docs/ERROR_CODES.md

Implement exponential backoff for requests where the connection succeeds but upstream processing exceeds the allowed time. This often occurs with long-context tasks, image/video generation, or high service load.

```text
524 Timeout Occurred
```

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

### Chat Completion API Request

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/README.md

Use this cURL command to send a chat completion request to the Agnes AI API. Ensure your AGNES_API_KEY is set as an environment variable. Streaming is enabled by default.

```bash
curl https://apihub.agnes-ai.com/v1/chat/completions \
  -H "Authorization: Bearer $AGNES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "agnes-2.0-flash",
    "messages": [
      {
        "role": "user",
        "content": "Explain how to integrate an OpenAI-compatible API gateway."
      }
    ],
    "stream": true
  }'
```

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

### Retry on Gateway Timeout Error (522)

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/docs/ERROR_CODES.md

Use exponential backoff for transient network connection timeouts between the gateway and upstream services. This error can stem from local network issues, proxy misconfigurations, or DNS problems.

```text
522 Connection Timed Out
```

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

### Image Generation

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/MODEL_CATALOG.md

Generates images based on text or image inputs. Supports URL or Base64 output, and offers different models with varying capabilities for image editing and flexible sizing.

```APIDOC
## POST /v1/images/generations

### Description
Generates images based on text-to-image or image-to-image prompts. Supports URL or Base64 output.

### Method
POST

### Endpoint
/v1/images/generations

### Parameters
#### Request Body
- **prompt** (string) - Required - The text prompt to guide image generation.
- **image_input** (string) - Optional - An image input for image-to-image transformations.
- **output_format** (string) - Optional - Specifies the output format, e.g., 'url' or 'base64'.

### Request Example
```json
{
  "prompt": "A futuristic cityscape at sunset",
  "output_format": "url"
}
```

### Response
#### Success Response (200)
- **output** (string) - The generated image URL or Base64 data.

#### Response Example
```json
{
  "output": "https://example.com/image.png"
}
```
```

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

### Agnes AI API Base URL

Source: https://github.com/agnesai-labs/agnes-ai/blob/main/docs/FAQ.md

This is the base URL for all Agnes AI API requests. Ensure this is correctly configured in your application.

```text
https://apihub.agnes-ai.com/v1
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.