Documentation Index
Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt
Use this file to discover all available pages before exploring further.
Anyfast is compatible with the Volcengine Ark Chat API. If you’re already using the Ark SDK or calling the Ark API directly, switching to Anyfast requires only a base URL change — no code rewrite needed.
Endpoints
POST https://www.anyfast.ai/v1/chat/completions
POST https://www.anyfast.ai/v1/responses
Authentication
Authorization: Bearer YOUR_API_KEY
Supported models
| Model | Description |
|---|
| doubao-seed-2.0-pro | Doubao Seed 2.0 Pro — most capable |
| doubao-seed-2.0-code | Doubao Seed 2.0 Code — optimized for coding |
| doubao-seed-2.0-lite | Doubao Seed 2.0 Lite — balanced |
| doubao-seed-2.0-mini | Doubao Seed 2.0 Mini — fast and lightweight |
| doubao-seed-1-8-251228 | Doubao Seed 1.8 |
| doubao-seed-1-6-flash-250828 | Doubao Seed 1.6 Flash — fast inference |
| doubao-seed-1-6-251015 | Doubao Seed 1.6 |
| doubao-seed-1-6-lite-251015 | Doubao Seed 1.6 Lite |
| doubao-seed-1-6-vision-250815 | Doubao Seed 1.6 Vision — multimodal |
| glm-4.7 | GLM-4-7 |
| Content | Chat API type | Chat API data field | Responses API type | Responses API data field |
|---|
| Text | text | text | input_text | text |
| Image | image_url | image_url.url | input_image | image_url (string) |
| Video | video_url | video_url.url + video_url.fps | input_video | video_url (string) + fps |
| Document | — | — | input_file | file_url or file_data + filename |
All content types support both URL and Base64 data URI formats.
Features
- Streaming — Set
stream: true for real-time token streaming via SSE
- Function calling — Use the
tools and tool_choice parameters
- Reasoning — Models return
reasoning_content with chain-of-thought
- Vision — Send images via
image_url / input_image content blocks
- Video understanding — Send videos via
video_url / input_video with optional fps control
- Document understanding — Send PDF/documents via
input_file (Responses API only)
- Multi-turn conversations — Include full message history in
messages / input
Chat Completions API
Text
curl https://www.anyfast.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-2.0-pro",
"messages": [
{"role": "user", "content": "Hello!"}
]
}'
Image (URL)
curl https://www.anyfast.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"messages": [
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
{"type": "text", "text": "What is in this image?"}
]
}
],
"max_tokens": 100
}'
Image (Base64)
curl https://www.anyfast.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"messages": [
{
"role": "user",
"content": [
{"type": "image_url", "image_url": {"url": "data:image/png;base64,{BASE64_IMAGE}"}},
{"type": "text", "text": "What is in this image?"}
]
}
]
}'
Video (URL + fps)
The fps parameter controls frame extraction rate (frames per second). Default: 1, range: 0.2–5.
curl https://www.anyfast.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"messages": [
{
"role": "user",
"content": [
{"type": "video_url", "video_url": {"url": "https://example.com/clip.mp4", "fps": 2}},
{"type": "text", "text": "What buildings appear in this video?"}
]
}
],
"max_tokens": 200
}'
Video (Base64)
curl https://www.anyfast.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"messages": [
{
"role": "user",
"content": [
{"type": "video_url", "video_url": {"url": "data:video/mp4;base64,{BASE64_VIDEO}"}},
{"type": "text", "text": "What is in this video?"}
]
}
]
}'
Responses API
Text
curl https://www.anyfast.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-2.0-pro",
"input": "Hello!"
}'
Image (URL)
curl https://www.anyfast.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"input": [
{
"role": "user",
"content": [
{"type": "input_image", "image_url": "https://example.com/photo.jpg"},
{"type": "input_text", "text": "What is in this image?"}
]
}
]
}'
Video (URL + fps)
curl https://www.anyfast.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-1-6-251015",
"input": [
{
"role": "user",
"content": [
{"type": "input_video", "video_url": "https://example.com/clip.mp4", "fps": 1},
{"type": "input_text", "text": "What is in this video?"}
]
}
]
}'
Document (URL)
Document understanding is only available via the Responses API.
curl https://www.anyfast.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-2.0-lite",
"input": [
{
"role": "user",
"content": [
{"type": "input_file", "file_url": "https://example.com/document.pdf"},
{"type": "input_text", "text": "Summarize this document"}
]
}
]
}'
Document (Base64)
curl https://www.anyfast.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seed-2.0-lite",
"input": [
{
"role": "user",
"content": [
{"type": "input_file", "file_data": "data:application/pdf;base64,{BASE64_PDF}", "filename": "document.pdf"},
{"type": "input_text", "text": "Summarize this document"}
]
}
]
}'
fps parameter
| fps | Use case |
|---|
| 0.2–0.5 | Static scenes, surveillance footage |
| 1 (default) | General purpose |
| 2–5 | Fast action, sports, motion counting |
File size limits
| Method | Image | Video | Document |
|---|
| URL | < 10 MB | < 50 MB | < 50 MB |
| Base64 | < 10 MB (body < 64 MB) | < 50 MB (body < 64 MB) | < 50 MB (body < 64 MB) |
Streaming example
stream = client.chat.completions.create(
model="doubao-seed-2.0-pro",
messages=[
{"role": "user", "content": "Write a short poem"}
],
stream=True
)
for chunk in stream:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="")