Your first HIPS inference request
The first request should be small and easy to inspect. This quickstart shows the setup for a supported chat-completion model using familiar clients.
The API root is https://ai.hips.com/v1; a key comes from the Console and a supported model or deployment identifier from the catalog. The environment variables below are configuration names, not live credentials or service addresses.
pip install openaiimport osfrom openai import OpenAI client = OpenAI( api_key=os.environ["HIPS_API_KEY"], base_url=os.environ["HIPS_BASE_URL"], # https://ai.hips.com/v1)result = client.chat.completions.create( model=os.environ["HIPS_MODEL"], messages=[{"role": "user", "content": "Explain GPU inference in two sentences."}],)print(result.choices[0].message.content)- Body
- choices[0].message.content<the answer>usage{ prompt_tokens, completion_tokens, total_tokens }
- Headers
- x-hips-request-idreq_...x-hips-cost-micros<integer, USD micro-dollars>
Confirm the client version, route, model, and supported fields in this documentation before using them. Keep keys on the server or in an appropriate secret store, rather than shipping them in a public browser application.
Every route is relative to the base URL, https://ai.hips.com/v1, the value of HIPS_BASE_URL that each sample names in its comment.
A chat completion in OpenAI's shape. Its id is the request id (req_...), the same value as the x-hips-request-id header, so a log line and a support question name the same thing. usage holds the token counts; the charge is in the x-hips-cost-micros header, never in usage. The Usage and Requirements and headers pages list every field.
One guide per provider-style client and version is added only with a validated row in the compatibility matrix. None exists at launch.
Related sheets
- Sheet
- 02 of 20
- Updated
- 2026-11-11