Call an InferCrane model
InferCrane Model APIs expose qualified open weight models through the OpenAI chat completions contract. Your application keeps one client while InferCrane operates the serving configuration, capacity, and release path behind it.The catalog is availability-authoritative. It lists a model only when an operator has installed a
current supplier, price, protocol, and capacity contract. If no qualified offer is available, use
BYOC or connect an existing endpoint; InferCrane does not route to an undisclosed fallback.
Create an API key
Sign in to the InferCrane console, choose a model, and create a scoped API key.
Send your first request
Set the key in your shell. Keep it on the server and never commit it to source control.Install the official Python client with
python -m pip install openai. For TypeScript, install it
with npm install openai.Use InferCrane in coding agents
The same key and endpoint work in coding agents that accept an OpenAI-compatible provider. Keep the key in an environment variable instead of committing it to a project configuration file.- OpenCode
- Kilo Code
- Cline
Add the provider to
opencode.json, then run /models and select
infercrane/qwen3.8-27b.Discover available models
Availability and prices can change as capacity and qualification evidence change. Read the live catalog instead of copying a stale model list into your application.qwen3.8-27b with:
These are serving limits for the current InferCrane release, not the maximum capabilities stated by
the base model publisher.
Stream tokens
Setstream: true and consume standard server sent events. The final chunk includes normal OpenAI
compatible completion metadata.
Handle capacity safely
InferCrane returns429 Too Many Requests before an overloaded request enters an unbounded queue.
Retry with exponential backoff and jitter. Respect Retry-After when it is present, and reuse your
application request ID when retrying an operation that must be idempotent.
Inference prompts and responses are not retained for model training. See the
privacy policy for the current service and subprocessors boundary.