Skip to main content
POST
/
v1
/
responses
curl --request POST \
  --url https://api.shuyou.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-5.5-pro",
  "input": "Hello!"
}
'
{
  "id": "resp_example",
  "object": "response",
  "created_at": 1741569952,
  "status": "completed",
  "model": "openai/gpt-5.5-pro",
  "output": [
    {
      "type": "message",
      "id": "msg_example",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! How can I help you today?",
          "annotations": []
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 19,
    "output_tokens": 10,
    "total_tokens": 29
  }
}

Authorizations

​
Authorization
string
header
required

Authorization: Bearer YOUR_API_KEY

Body

application/json
​
model
string
required

Model ID (provider/model_name). Use the slug from List Models.

Example:

"openai/gpt-5.5-pro"

​
input

Plain-text input (equivalent to a single user message).

​
instructions
string

System/developer instructions. Not carried over when using previous_response_id.

​
previous_response_id
string

ID of the previous response for multi-turn conversations. Cannot be used with conversation.

​
conversation

Associates this response with a conversation.

​
prompt
object

Reference a prompt template and variables.

​
include
enum<string>[]

Additional output data to include in the response.

Available options:
web_search_call.action.sources,
computer_call_output.output.image_url,
message.input_image.image_url,
message.output_text.logprobs,
reasoning.encrypted_content
​
max_output_tokens
integer

Upper bound for generated tokens, including visible output and reasoning tokens.

​
max_tool_calls
integer

Maximum total built-in tool calls processed in this response.

​
parallel_tool_calls
boolean
default:true

Whether to allow parallel tool calls.

​
reasoning
object

Reasoning model configuration.

​
text
object

Text output configuration (plain text or structured JSON).

​
temperature
number
default:1
Required range: 0 <= x <= 2
​
top_p
number
default:1
Required range: 0 <= x <= 1
​
top_logprobs
integer
Required range: 0 <= x <= 20
​
truncation
enum<string>
default:disabled

Context truncation when input exceeds the context window.

Available options:
auto,
disabled
​
tools
object[]

Tools the model may call. ShuYou does not support file_search, code_interpreter, or image_generation tools.

​
tool_choice
Available options:
none,
auto,
required
​
store
boolean
default:true

Whether to store the response for later retrieval.

​
stream
boolean
default:false

Stream the response via server-sent events.

​
stream_options
object
​
prompt_cache_key
string

Cache key for similar requests (replaces legacy user).

​
prompt_cache_retention
enum<string>
Available options:
in_memory,
24h
​
safety_identifier
string

Stable hashed user identifier for abuse detection.

Maximum string length: 64
​
provider
object

ShuYou: multi-provider routing.

​
model_routing_config
object

ShuYou: model selection within a provider.

Response

Response object, or SSE stream when stream is true

​
id
string
​
object
enum<string>
Available options:
response
​
created_at
integer
​
status
enum<string>
Available options:
completed,
failed,
in_progress,
incomplete,
cancelled,
queued
​
model
string
​
output
object[]
​
usage
object
​
error
object
​
incomplete_details
object