Route the OpenAI Assistants & Responses API through Jents

Agents built on OpenAI's Assistants or Responses API route the same way — set the client's base URL + key and the threads and runs flow through the gateway.

1. Create the source in Jents

Capture AI source → "AI you build or run" → "Yes — I can point it at a URL." Name it, create it, Provision the key on the Keys tab, and copy your gateway URL + key.

2. Point the client at the gateway

from openai import OpenAI

client = OpenAI(
    base_url="https://YOUR-GATEWAY-URL",
    api_key="YOUR-AGENT-KEY",
)

# Responses API
client.responses.create(model="gpt-4o", input="Summarize this ticket…")

# Assistants API — same client; threads and runs route through Jents
assistant = client.beta.assistants.create(model="gpt-4o", instructions="…")

Everything you already do with the SDK stays the same — only the base URL + key change.

3. Run it and confirm

Create a run → the source's Keys tab flips to "Working ✓" and the spend appears in Observability.

The Assistants API is being superseded by the Responses API — both route through Jents identically.