Featherless + Stream Deck

List the models available on Featherless (GET /v1/models). Returns model objects each containing an id field to pass as the model prop in Create Chat Completion and Create Text Completion. The catalog is very large (~22k models), so results are paged (100 per page by default) and each model is trimmed to key fields (id, name, model_class, context_length, max_completion_tokens, available_on_current_plan); use q to search, page to page through, or fields to change which fields are returned. Example: q=Qwen returns Qwen-family models with ids like Qwen/Qwen3-8B (pass that id as the model prop in a completion). Results are paged (100 per page); increment page to fetch more. Because a page size is always sent, the response also includes pagination (current_page, total_pages, total_items) and a total count. View docs.

Generate a text completion from a raw prompt using a Featherless-hosted model (POST /v1/completions). Returns a completion object whose choices[0].text holds the generated text, plus a usage token breakdown. This is a distinct legacy-style completion endpoint from Create Chat Completion. Use List Models first to discover valid model IDs. Example: model=Qwen/Qwen3-0.6B, prompt="The capital of France is" returns Paris in choices[0].text. View docs.

Generate a chat completion using a Featherless-hosted model (POST /v1/chat/completions). Returns a completion object whose choices[0].message.content holds the model's reply, plus a usage token breakdown. Use List Models first to discover valid model IDs to pass to the model prop. Example: model=Qwen/Qwen3-0.6B, messages=[{"role":"user","content":"What is 2 + 2?"}] returns a reply of 4 in choices[0].message.content. View docs.