v35

latestOpenAPI 3.0.0Proprietaryraw.githubusercontent.com2026-04-1656176283.0 KB

LLM

Language model chat

Interact with language models via OpenAI's chat completions API

post/v1/chat/completions

Request body

frequency_penaltynumber

logit_biasobject

LogitBias is must be a token id string (specified by their token ID in the tokenizer), not a word string. incorrect: "logit_bias":{"You": 6}, correct: "logit_bias":{"1639": 6} refs: https://platform.openai.com/docs/api-reference/chat/create#chat/create-logit_bias

logprobsboolean

LogProbs indicates whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message. This option is currently not available on the gpt-4-vision-preview model.

max_tokensinteger

modelstring

ninteger

parallel_tool_callsboolean

Disable the default behavior of parallel tool calls by setting it: false.

presence_penaltynumber

seedinteger

stopstring[]

streamboolean

temperaturenumber

{"stackTrail":"components:schemas:schemas.ChatRequest:properties:tool_choice","oasType":"schema","type":"unknown","description":"This can be either a string or an ToolChoice object."}

{"stackTrail":"components:schemas:schemas.ChatRequest:properties:tools","oasType":"schema","type":"unknown"}

top_logprobsinteger

TopLogProbs is an integer between 0 and 5 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used.

top_pnumber

userstring

Response

createdinteger

idstring

modelstring

objectstring

system_fingerprintstring