Optional additionalA container for additional, undeclared properties. This is a holder for any undeclared properties as specified with the 'additionalProperties' keyword in the OAS document.
Optional anthropicAnthropic-specific metadata for an inference request.
Optional azureAzure OpenAI-specific metadata for an integration account or inference request.
Optional bedrockAmazon Bedrock-specific metadata for an inference request.
Optional frequencyPenalty for token frequency to reduce repetition.
Optional jsonJSON schema for structured output, if supported by the model.
Optional maxMaximum number of completion tokens to generate (alternative to max_tokens for some providers).
Optional maxMaximum number of tokens to generate.
List of messages in an inference conversation.
The model identifier to use for inference.
Optional openaiOpenAI-specific metadata for an inference request.
Optional presencePenalty for token presence to encourage topic diversity.
Optional temperatureSampling temperature between 0 and 2. Higher values produce more random output.
Optional toolsList of tools available to the model.
Optional topKTop-K sampling parameter.
Optional topPNucleus sampling probability mass.
Optional vertexVertex AI-specific metadata for an integration account or inference request.
Generated using TypeDoc
Parameters for an LLM inference request.