Rodium AI
Rodium AI docs
Guides

Chat completions

Our primary endpoint — assemble messages[], set model to a provider-scoped id (e.g. openai/gpt-4o), tune decoding, and optionally stream SSE.

Parameters

ParameterTypeRequiredDescription
modelstringRequiredProvider-scoped model id (e.g. openai/gpt-4o, anthropic/claude-3-5-sonnet). Use GET /v1/models or the Models page to list all ids.
messagesarrayRequiredArray of message objects with role and content fields
max_tokensintegerOptionalMaximum tokens to generate. Defaults to model maximum.
temperaturenumberOptionalSampling temperature between 0 and 2. Higher = more random.
top_pnumberOptionalNucleus sampling probability mass. Between 0 and 1.
streambooleanOptionalIf true, stream partial deltas as Server-Sent Events.
stopstring | arrayOptionalSequences where the API will stop generating tokens.

OpenAI SDK mode + cURL

cURL:

Sample JSON

Endpoint reference: POST /v1/chat/completions