Skip to main content
POST
/
v1
/
responses
curl --request POST \ --url https://direct.evolink.ai/v1/responses \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model": "doubao-seed-2.0-pro", "input": "Please introduce yourself" } '
{
  "id": "resp_02177148667427813c33c36521378d02b2c8389204fa8c3e2f63e",
  "object": "response",
  "created_at": 1771486674,
  "model": "doubao-seed-2-0-code-preview-260215",
  "status": "completed",
  "output": [
    {
      "id": "rs_0217****404a",
      "type": "reasoning",
      "summary": [
        {
          "text": "<string>",
          "type": "summary_text"
        }
      ],
      "status": "completed"
    }
  ],
  "service_tier": "default",
  "instructions": "<string>",
  "previous_response_id": "<string>",
  "max_output_tokens": 32768,
  "temperature": 123,
  "top_p": 123,
  "thinking": {},
  "tools": "<array>",
  "tool_choice": "<unknown>",
  "parallel_tool_calls": true,
  "text": {},
  "usage": {
    "input_tokens": 88,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 230,
    "output_tokens_details": {
      "reasoning_tokens": 211
    },
    "total_tokens": 318
  },
  "caching": {},
  "store": true,
  "expire_at": 1756539922,
  "error": {},
  "incomplete_details": {}
}
BaseURL: The default BaseURL is https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.

Authorizations

​
Authorization
string
header
required

All APIs require Bearer Token authentication

Get API Key:

Visit the API Key Management Page to get your API Key

Add to request headers:

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
enum<string>
default:doubao-seed-2.0-pro
required

Chat model name

  • doubao-seed-2.0-pro: Flagship, strongest overall capability
  • doubao-seed-2.0-lite: Lightweight, faster speed
  • doubao-seed-2.0-mini: Ultra-fast, quickest response
  • doubao-seed-2.0-code: Code-specialized
Available options:
doubao-seed-2.0-pro,
doubao-seed-2.0-lite,
doubao-seed-2.0-mini,
doubao-seed-2.0-code
Example:

"doubao-seed-2.0-pro"

​
input
required

Input content. Supports two formats:

1. Plain text string: Equivalent to text input from the user role

2. Element list (array): Contains multiple input types including messages, context, tool calls, etc.

​
instructions
string | null

Insert a system message or developer instruction as the first instruction in the model context

Note:

  • When used with previous_response_id, instructions from the previous response are not inherited
  • Cannot be used together with caching
​
previous_response_id
string | null

Unique identifier of the previous model response, used to implement multi-turn conversations

Note:

  • When provided, it will include the input and response content from the previous round, and the input tokens for the current request will increase accordingly
  • In continuous multi-turn conversations, it is recommended to add approximately 100ms delay between each request
​
expire_at
integer

Storage expiration time, UTC Unix timestamp (seconds)

Note:

  • Value range: (creation time, creation time + 604800], i.e., maximum retention of 7 days
  • Default: creation time + 259200 (3 days)
  • Applies to both store and caching
  • Cache storage is billed by time, less than 1 hour is counted as 1 hour
​
max_output_tokens
integer | null

Maximum number of output tokens from the model, including model response and chain-of-thought content

Example:

32768

​
thinking
object

Controls whether the model enables deep thinking mode

​
reasoning
object

Limit deep thinking workload, reducing it can make responses faster and use fewer tokens

​
caching
object

Whether to enable context caching

Note: Cannot be used together with instructions field or tools field (except Function Calling)

​
store
boolean | null
default:true

Whether to store the generated model response for later retrieval via API

  • true: Store the current model response
  • false: Do not store
​
stream
boolean | null
default:false

Whether to stream the response content

  • false: Return all content at once after the model finishes generating
  • true: Return chunks progressively via SSE protocol, ending with a data: [DONE] message
​
temperature
number | null
default:1

Sampling temperature, controls output randomness

  • Value range: [0, 2]
  • Lower values are more deterministic, higher values are more random
  • It is recommended to adjust only one of temperature or top_p

Note: doubao-seed-2.0-pro and doubao-seed-2.0-lite are fixed at 1, manual specification will be ignored

Required range: 0 <= x <= 2
​
top_p
number | null
default:0.7

Nucleus sampling probability threshold

  • Value range: [0, 1]
  • It is recommended to adjust only one of temperature or top_p

Note: doubao-seed-2.0-pro and doubao-seed-2.0-lite are fixed at 0.95, manual specification will be ignored

Required range: 0 <= x <= 1
​
text
object

Format definition for model text output

​
tools
object[]

List of tools the model can call

Supported tool types:

  • function: Custom function (Function Calling)
  • web_search: Web search
  • doubao_app: Doubao App
  • image_process: Image processing
  • mcp: MCP tools
  • knowledge_search: Private knowledge base search
​
tool_choice

Controls whether the model calls tools

String mode:

  • none: Do not call tools
  • required: Must call tools
  • auto: Model decides (default)

Object mode: Specify a particular tool to call

Available options:
none,
auto,
required
​
max_tool_calls
integer

Maximum number of tool call rounds (unlimited calls per round)

  • Value range: [1, 10]
  • Web Search default: 3
  • Image Process default: 10 (modification not supported)
  • Knowledge Search default: 3

Note: This parameter operates on a best-effort basis; the actual number of calls is influenced by model inference performance and other factors

Required range: 1 <= x <= 10
​
context_management
object

Context management strategy to help the model effectively utilize the context window

Response

Response generated successfully

​
id
string

Unique identifier for this response

Example:

"resp_02177148667427813c33c36521378d02b2c8389204fa8c3e2f63e"

​
object
enum<string>

Object type, fixed as response

Available options:
response
Example:

"response"

​
created_at
number

Unix timestamp (seconds) of creation time

Example:

1771486674

​
model
string

Actual model name and version used

Example:

"doubao-seed-2-0-code-preview-260215"

​
status
enum<string>

Response status

  • completed: Generation completed
  • in_progress: Generation in progress
  • incomplete: Incomplete
  • failed: Failed
Available options:
completed,
in_progress,
incomplete,
failed
Example:

"completed"

​
output
(Chain-of-thought output · object | Message output · object | Tool call output · object)[]

Model output content list, including chain-of-thought output, message output, tool call output, etc.

​
service_tier
string

Service tier for this request

  • default: Default service tier
  • scale: Used guaranteed package quota
Example:

"default"

​
instructions
string | null

System instructions used for this request

​
previous_response_id
string | null

Referenced previous response ID

​
max_output_tokens
integer

Maximum number of output tokens from the model

Example:

32768

​
temperature
number | null

Sampling temperature used

​
top_p
number | null

top_p value used

​
thinking
object | null

Thinking mode configuration used

​
tools
array | null

List of tools used

​
tool_choice
any | null

Tool choice configuration used

​
parallel_tool_calls
boolean | null

Whether parallel tool calls are allowed

​
text
object | null

Text output format configuration

​
usage
object

Token usage statistics

​
caching
object

Caching configuration

​
store
boolean

Whether the response was stored

​
expire_at
integer

Storage expiration time (Unix timestamp)

Example:

1756539922

​
error
object | null

Error information, null on success

​
incomplete_details
object | null

Detailed reason for incompleteness