Inference

Create a chat completion

post/openai/v1/chat/completions

Request

  • Base URL: https://api.tinyhumans.ai
  • URL: https://api.tinyhumans.ai/openai/v1/chat/completions
  • Auth: HTTP bearer

Request body

modelstring required
streamboolean
temperaturenumber
max_tokensinteger
thread_idstring

Optional caller-supplied conversation identifier. Persisted on the InferenceLog and on the charge (CreditTransaction, ledger legs, usage log) so a conversation's spend can be grouped and summed — see GET /openai/v1/threads/{threadId}/usage. Echoed back as openhuman.thread_id.

Example request

{
  "model": "reasoning-v1"
}

Response

Chat completion response in OpenAI format, plus an openhuman object (usage, billing.charged_amount_usd, request_id — the x-request-id the charge is recorded under — and thread_id when one was sent). When streaming, the same object arrives in an event: openhuman-metadata frame before [DONE].

Changes

No recorded changes to this operation across all 1 revision of this API.