Responses

POST https://api.solcardinference.ai/v1/responses

Request and response follow the OpenAI Responses format. Responses are stateless: nothing is stored, so send the full conversation each time.

Field	Type	Notes
model	string	Required. A model ID.
input	string | array	Required. A string, or message, function_call and function_call_output items with text content.
instructions	string
stream	boolean
max_output_tokens	integer	Up to 32,768.
temperature	number
top_p	number
tools	array	Function tools only.
tool_choice	string | object
parallel_tool_calls	boolean
reasoning	object	Default { "effort": "none" }. See reasoning.
text	object	Output format, e.g. { "format": { "type": "json_schema", ... } }.
truncation	string
user	string

Not supported: previous_response_id and store: true (400 unsupported_parameter), non-function tools, and non-text content.

Example request

curl https://api.solcardinference.ai/v1/responses \
  -H "Authorization: Bearer $SOLCARD_INFERENCE_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "flash", "input": "Hi" }'