SaaufAI
  • Loading…
  • WispsAssistants that keep working while you're awayPage
  • DocsGuides with screenshotsPage
  • Quick startDocs · first Wisp or first API callPage
  • API referenceDocs · Chat Completions, streaming, toolsPage
  • Create a WispDocs · step by stepPage
  • BlogNews and notesPage
  • All modelsDirectoryPage
  • CompaniesWho makes the modelsPage
  • Compare disclosuresEvery model, every questionPage
  • PoliciesTerms, privacy, acceptable usePage

Playground

Try any model in your browser before you write code.

Open Playground, pick a model and start typing. Conversations in the Playground aren't stored.

The Playground: model picker, system prompt, temperature and max output on the left, the chat on the rightThe Playground: model picker, system prompt, temperature and max output on the left, the chat on the right
Settings on the left; “Get code” turns the current chat into an API request.
  • GLM 4.5 Flash runs on your free allowance. Other models are paid from credit at their listed price.
  • Set a system prompt, temperature and max output tokens.
  • Get code shows the current chat as a ready-to-run curl request. The API reference has the same in Python and JavaScript.
  • With Pollinations connected, its models appear in their own group, paid from your Pollen.

When your free allowance runs low, a bar above the message box tells you. See Credit and free usage.