Seed Text Generation

Seed is ByteDance's large language model series with strong Chinese understanding and generation. It is fully OpenAI-compatible, so you can migrate existing OpenAI apps with zero code changes.

Endpoint

Seed provides two compatible endpoints. They behave identically — choose either:

• OpenAI-compatible: POST $URL/v1/chat/completions
• Volcengine native: POST $URL/api/v3/chat/completions

When using the OpenAI SDK, set base_url to either $URL/v1 or $URL/api/v3.

Supported Models

Model	Description
seed-2.0-pro	Flagship, best overall capability
seed-2.0-lite	Lightweight, high cost-efficiency
seed-2.0-mini	Mini, extreme speed
seed-2.1-pro	2.1 flagship, enhanced reasoning & long context
seed-2.1-turbo	2.1 high-speed, low latency

All models also support a doubao- prefix (e.g. doubao-seed-2.0-pro); behavior is identical.

See the Console "Model Market" for more versions.

Parameters

Param	Type	Required	Description
model	string	yes	Model name above
messages	array	yes	Conversation messages; each has role (system/user/assistant) and content
stream	boolean	no	Stream the response, default false
temperature	number	no	Sampling temperature 0–2, default 1
top_p	number	no	Nucleus sampling probability 0–1, default 1
max_tokens	integer	no	Max tokens to generate
presence_penalty	number	no	Presence penalty −2–2, default 0
frequency_penalty	number	no	Frequency penalty −2–2, default 0
stop	string / array	no	Stop sequence(s)
response_format	object	no	Force a specific output format (e.g. {"type":"json_object"})

Request Example

curl

curl $URL/v1/chat/completions \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seed-2.0-pro",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in one sentence"}
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(api_key="YOUR_API_KEY", base_url="$URL/v1")
resp = client.chat.completions.create(
    model="seed-2.0-pro",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence"}],
)
print(resp.choices[0].message.content)

TypeScript

import OpenAI from 'openai'

const client = new OpenAI({
  apiKey: process.env.YOUR_API_KEY,
  baseURL: '$URL/v1',
})
const resp = await client.chat.completions.create({
  model: 'seed-2.0-pro',
  messages: [{ role: 'user', content: 'Explain quantum computing in one sentence' }],
})
console.log(resp.choices[0].message.content)

Response Fields

Field	Type	Description
id	string	Unique request ID
object	string	Always chat.completion
created	integer	Creation timestamp (seconds)
model	string	Model actually used
choices	array	Candidate completions
choices[].index	integer	Candidate index
choices[].message	object	The message object
choices[].message.role	string	Always assistant
choices[].message.content	string	Reply text
choices[].finish_reason	string	Stop reason (stop/length/content_filter etc.)
usage	object	Token usage
usage.prompt_tokens	integer	Input tokens
usage.completion_tokens	integer	Output tokens
usage.total_tokens	integer	Total tokens

Response Example

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "seed-2.0-pro",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses superposition and entanglement of qubits to process information in parallel, beating classical computers on certain problems."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 38,
    "total_tokens": 50
  }
}