OneKeyModel LogoOneKeyModel

API Documentation

Easily integrate text, image, and video generation models through a unified OpenAI-compatible API.

Base URL & Authentication

All API requests require the unified Base URL and your API Key (Token) in the Authorization header.

Base URL
https://api.onekeymodel.com/v1
Authorization Header Format
Authorization: Bearer YOUR_API_KEY

Text Completions APIPOST /v1/chat/completions

Used for chatting, coding, translating, etc. with text models. Fully compatible with OpenAI's `/v1/chat/completions` standard.

cURL Example

bash
curl https://api.onekeymodel.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "deepseek-chat",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ]
  }'

Python Example

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.onekeymodel.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"}
    ]
)

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

Image Generations APIPOST /v1/images/generations

Used for generating images. Supports Midjourney, DALL-E 3, wan2.7-image, and more.

cURL Example

bash
curl https://api.onekeymodel.com/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "wan2.7-image",
    "prompt": "A beautiful sunset over the mountains, digital art",
    "n": 1,
    "size": "1024x1024"
  }'

Python Example

python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.onekeymodel.com/v1"
)

response = client.images.generate(
    model="wan2.7-image",
    prompt="A beautiful sunset over the mountains, digital art",
    n=1,
    size="1024x1024"
)

print(response.data[0].url)

Video Generations API

Since video generation takes longer (like wan2.7-t2v), the process is split into two steps: submitting the task and polling for the result.

Step 1: Submit Video Generation TaskPOST /v1/video/generations
Submit the generation parameters to the API. It will immediately return a task record with status `in_progress` or `queued`, containing the `id` (task_id).
bash
curl -X POST https://api.onekeymodel.com/v1/v1/video/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "wan2.7-t2v",
    "prompt": "A futuristic city in cyberpunk style, flying cars",
    "resolution": "1280*720"
  }'

# Response Example:
# {
#   "id": "148ed382-b7e1-4357-9d29-c70f61cd3a2f",
#   "status": "in_progress",
#   "created_at": 1715865000
# }
Step 2: Poll Task StatusGET /v1/video/generations/:task_id
Use the `id` from the previous step to query the task status every few seconds. When the status changes to `succeeded` or `completed`, the final video URL will be available.
bash
curl -X GET "https://api.onekeymodel.com/v1/video/generations/148ed382-b7e1-4357-9d29-c70f61cd3a2f" \
  -H "Authorization: Bearer $YOUR_API_KEY"

# Response Example (When Finished):
# {
#   "id": "148ed382-b7e1-4357-9d29-c70f61cd3a2f",
#   "status": "succeeded",
#   "created_at": 1715865000,
#   "video_url": "https://example.com/video.mp4"
# }