Tool to generate a chat-style completion. Use after assembling messages and selecting a model. Supports streaming and function calls. Response format varies across models; use explicit prompt instructions to standardize output. Provider-level rate limits and moderation policies…
nintegerNumber of completion choices to generate.
stopSequences where the API will stop generating further tokens.
userstringA unique identifier for the end-user to help detect abuse.
modelRequiredstringID of the model to use for the chat completion. Must exactly match an ID returned by OPENROUTER_LIST_AVAILABLE_MODELS; typos or approximate names cause request failures.
top_pnumberNucleus sampling probability, between 0 and 1.
streambooleanWhether to stream back partial message deltas.
messagesRequiredarrayList of conversation messages to provide as context.
functionsarrayList of functions the model may call. Only supported by models that explicitly advertise function-calling capability via OPENROUTER_LIST_AVAILABLE_MODELS. Each function schema must be valid JSON; malformed schemas cause runtime failures regardless of prompt correctness.
logit_biasobjectAdjust the likelihood of specified tokens.
max_tokensintegerMaximum number of tokens to generate.
temperaturenumberSampling temperature to use, between 0 and 2.
function_callControl function call behavior: 'none', 'auto', or specify {'name': function_name}.
dataRequiredData from the action execution
errorstringError if any occurred during the execution of the action
successfulRequiredbooleanWhether or not the action execution was successful or not
API key connection. Risk level 2 of 5.
Free Action
No published Skills explicitly reference this Action yet.