OpenAI-compatible chat completions endpoint with integrated security, PII masking, and web search.
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Identifier for the model to use (e.g., openai/gpt-4o, grok/grok-beta)
openai/gpt-4o-mini, openai/gpt-4o, google/gemini-2.0-flash-exp, xai/grok-beta, deepseek/deepseek-chat, deepseek/deepseek-reasoner "openai/gpt-4o"
A list of messages comprising the conversation so far.
If set, partial message deltas will be sent as server-sent events.
Optional system prompt to override the default gateway behavior.
Enables tools. Defaults to true unless a custom system prompt is used.
Security mode for PII scanning.
disabled, obfuscate, block What sampling temperature to use, between 0 and 2.
0 <= x <= 2The maximum number of tokens to generate in the completion.