Skip to content
llms.party

Live playgrounds

Every button below sends a request through the gateway with the key you provide. Spend lands on that key's budget.

Gateway status: Checking…

API key

One key is shared by every playground on this page. It is written to this tab's sessionStorage and sent to the gateway as Authorization: Bearer. It is cleared when the tab closes.

Stored in this tab's sessionStorage and sent only to the gateway as a bearer token. It is cleared when the tab closes. Type over the field to replace the saved key.

Key usage and balance

GET /v1/usage shows the budget left, current-window spend and model access for the saved key. Check it before a paid video run; the fields are documented under Usage and balance.

Key usage

GET /v1/usage

Enter an API key above to see its budget and spend.

Chat

Non-streaming or SSE, at the temperature you choose.

Try a completion

POST /v1/chat/completions

Response

No response yet.

Model discovery

GET /v1/models returns the groups this key can call. Grants are frozen when the key is issued, so the list rarely changes for a given key.

What can this key call?

GET /v1/models
deepseek-flashdeepseek-v4-prominimax-h3minimax-h3-maxseedance

Check your own key to confirm the groups it is scoped to.

Video

Create a MiniMax H3, H3-Max or BytePlus Seedance job, poll it and play the result when it finishes. Keep the prompt short and the clip at the minimum duration the selected model allows while testing.

Generate a video

POST /v1/videos

MiniMax H3 · billed per second

Raw requests

Pick a public endpoint, edit the JSON body, and inspect the raw status and response. Useful for reproducing a support report.

Raw request

GET /v1/models