Models

Qwen3.8-27B through one OpenAI-compatible API.

Use Qwen3.8-27B for text, images, and tools on paid plans.

Paid subscribers can also choose yolo, a configurable route initially backed by the same model.

Use GET /v1/models with your API key to discover models. Model discovery remains available on Free accounts, but API inference requires a paid plan.

Create account → View request examples
Model reference

Exact model IDs

Works with clients that support a custom base URL and OpenAI-compatible chat completions.

Public model IDs, model context windows, and subscription access.
Model IDContextAccess
qwen3.8-27bQwen3.8-27B. Text, images, and tools on paid plans 256K Paid inference access
yoloOptional paid route; server-side target can change 256K Paid inference access
yolo-smallUse in /v1/chat/completions 128K Paid inference access
yolo-128kUse in /v1/chat/completions 128K Paid inference access
Demand

Peak hours, past 7 days

25%50%75%100%1218Oct 1700061218Oct 1800061218Oct 1900061218Oct 2000061218Oct 2100061218Oct 2200061218Oct 230006Server max capacity

*Chart shown in EST

Try it yourself

Test the API with your own workload.

Free accounts include 0 requests/week. Choose a paid plan to run API inference with your own prompts.

Create account Compare plans