Volcengine (火山引擎)
ByteDance Volcano Ark and Doubao models across text, vision, audio, image, and video.
Overview
Volcengine (火山引擎) is ByteDance's cloud platform. Its Volcano Ark (火山方舟) service provides access to the Doubao (豆包) model family across text, vision, and multimedia generation.
Official Website: https://www.volcengine.com API Documentation: https://www.volcengine.com/docs/82379
Key features
- Doubao model family — Chat and reasoning with strong Chinese-language performance
- Vision — Image understanding
- Embeddings — Text embeddings for semantic search
- Audio — Text-to-speech and speech-to-text
- Image & video generation — Text-to-image and text-to-video
- Realtime & voice clone — Low-latency audio and custom voice creation
Using Volcengine with Yunxin
Address Volcengine models using the provider/model convention by prefixing with volcengine/. Requests use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your Yunxin sk- API key.
Usage example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["YUNXIN_API_KEY"],
base_url="https://api.yuhuanstudio.com/v1"
)
response = client.chat.completions.create(
model="volcengine/model-id",
messages=[{"role": "user", "content": "你好！"}]
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.YUNXIN_API_KEY,
baseURL: "https://api.yuhuanstudio.com/v1",
});
const response = await client.chat.completions.create({
model: "volcengine/model-id",
messages: [{ role: "user", content: "你好！" }],
});
console.log(response.choices[0].message.content);curl https://api.yuhuanstudio.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $YUNXIN_API_KEY" \
-d '{
"model": "volcengine/model-id",
"messages": [{"role": "user", "content": "你好！"}]
}'Available models
Query the live catalog with the Models API:
curl "https://api.yuhuanstudio.com/v1/models?provider=volcengine" \
-H "Authorization: Bearer $YUNXIN_API_KEY"Capabilities and pricing are tracked per model. Use GET /v1/models?provider=volcengine and each model's capabilities array as the authoritative source rather than relying on a hardcoded list.
Official resources
How is this guide?