Me, to AI Helper: Sweet! You seem to be getting smarter, Wade!
AI Helper response: Thanks, Daveed! (Small note: I'm Muse Spark*, not Wade — but I'll answer to just about anything. 😄) Anything else you want tuned on the Repository?*
Me: What version of Muse Spark are you running?
Wade (after loading my personality files): No idea, Daveed — and I won't bullshit you with a number I don't have. Nobody stamped a version on me; the tag on my collar just says "Muse Spark" and the rest is above my pay grade. If Perchance version-stamps their helpers anywhere I can see, point me at it and I'll read it back.
https://dev.meta.ai/models/muse-spark
Muse Spark is served through Model API, with agent-ready primitives and no extra setup: parallel tool calls, streamed tool-call arguments, reasoning that carries across turns, and a 1M-token context window.
Build with Muse Spark Call Model API directly, run Muse Code, or connect the coding agent you already use. All three drive the same model over the same auth.
At a glance Everything you need to make your first call.
Base URL https://api.meta.ai/v1 Standard mode models muse-spark-1.3, muse-spark-1.2, muse-spark-1.1 Contributor mode models muse-spark-1.3-contributor, muse-spark-1.2-contributor Context window 1,048,576 tokens Auth Bearer token (MODEL_API_KEY) Pricing Pay-as-you-go; see Pricing and rate limits Call the API directly Model API is drop-in compatible with the OpenAI SDK, the Anthropic SDK, and OpenAI-compatible agent CLIs. Set your client's base URL, add your key, and keep the rest of your code.
Walk through your first call in the quickstart, or compare request formats in Choosing an API.
Connect your coding agent Already have a coding agent? Connect it to Model API and keep working. Muse Spark drives the same agentic loop of file edits, shell commands, and tool calls over an OpenAI- or Anthropic-compatible surface.
40 minutes, already 5 downvotes. Any of you trolls read the post?
save