Create Response
Responses API endpoint — provider resolved dynamically from DB.
Auth: Authorization: Bearer rsk_<ULID> Streaming: set stream=true for SSE chunks Rate limits: RPM and RPD enforced per key via Redis fixed-window counters Spend cap: enforced if key.spend_cap_usd is set Provider: resolved from model_pricing.provider (same as chat/completions)
Authentication
AuthorizationBearer
Bearer authentication of the form Bearer <token>, where token is your auth token.
Request
This endpoint expects an object.
input
model
template
variables
session_id
stream
max_output_tokens
temperature
top_p
seed
reasoning
tools
tool_choice
response_format
plugins
user
previous_response_id
instructions
thinking
caching
store
include
expire_at
max_tool_calls
context_management
text
timeout
Response
Successful Response