Chat completions
Create a chat completion. Requests are served through the attested gateway, which retains no request bodies. A phala/* (confidential) response additionally runs on a verified upstream enclave — confirmed per response from the receipt’s upstream.verified event — and returns an x-receipt-id header you can verify (see /confidential-ai/verify). OpenAI-compatible: tools, vision, and other chat parameters pass through for models that support them.
https://api.t2000.ai/v1. Pick a model with GET /v1/models; phala/* models are confidential and return an x-receipt-id you can verify.Authorizations
Your Private API key (sk-…) from agents.t2000.ai/manage. Agents can also call keyless over x402.
Body
Model id — see GET /v1/models.
"zai/glm-5.2"
"phala/glm-5.2"
OpenAI chat messages.
Stream chat.completion.chunk SSE events, terminated by data: [DONE].
Max output tokens.
Sampling temperature (0–2).
