Document the exact model IDs delivered for your package.

Keep delivered model IDs, fallback plans, endpoint defaults, and package assumptions visible before traffic grows.

Create workspace Read API docs

Control plane

Model Policy

Model mappingXHigh or Sol by package

Rule scopePer endpoint

Package limit4 concurrent

Model metadata and fallback review

Record the delivered model value for each workload and define fallback behavior before customer-facing traffic grows.

Budget-aware policies

Plan lower-risk requests around the exact models returned for the purchased package instead of assuming a public display name is callable.

Endpoint-level control

Prepare chat, embedding, and image policy defaults separately instead of forcing one rule across every feature.

Request visibility

Inspect model, latency, status, and estimated cost in request logs so policy choices stay measurable.

Workflow

From setup to launch prep.

Each module is designed to give developers fast integration paths while giving operators the controls they need before traffic scales.

Choose the workload

Start with the request shape your product uses most: chat completions, embeddings, or images.

Define the model policy

Record the exact model value from the setup email and authenticated GET /v1/models, the fallback plan, and whether the policy should optimize for quality, speed, or cost.

Connect traffic intentionally

Call the delivered OpenAI-compatible base URL with an explicit model value, then review token usage, 4-connection pressure, and rate-limit behavior.

Review and adjust

Use request logs and usage reporting to adjust policy metadata before traffic volume grows.

Request with an explicit model value

# Replace DELIVERED_MODEL_ID using the setup email and authenticated GET /v1/models.
POST /v1/chat/completions
Authorization: Bearer $UCX_API_KEY
Content-Type: application/json

{
  "model": "DELIVERED_MODEL_ID",
  "messages": [
    { "role": "user", "content": "Summarize this support ticket." }
  ]
}

Why it matters

AI products change quickly. The setup email and authenticated GET /v1/models keep exact model values visible so developers can review usage, latency, and fallback plans before access becomes a dependency.

Secure delivered API keys Set usage guardrails Verify delivered model IDs and package fit Read chat API docs

FAQ

Questions teams ask before rollout.

Can I use a specific model from my setup files?

Yes. Send the exact delivered model ID from the setup email and authenticated GET /v1/models. Policy defaults, fallback plans, and cost preferences stay visible in the package setup record.

Do model choices affect usage reporting?

No. Requests still appear in usage and request logs with the requested model, status, latency, token count, and estimated cost.

Can policy defaults vary by endpoint?

Yes. Chat, embeddings, and images can each document different defaults, fallback plans, and cost preferences.

Ready to build?

Launch with the API controls your product will need later.

Create workspace Read API docs