Last refreshed 2026-11-10. Next refresh: weekly.
Why use Muse Ember on Meta Model API?
Meta Model API offers Muse Ember with pay-as-you-go pricing at $0.10/1M input tokens. Meta Model API is Meta's developer API for accessing Muse Spark 1.1 in public preview, with OpenAI-compatible and Anthropic-compatible request formats, tool/function calling, structured output, and multimodal agentic workflows.
Compare Muse Ember across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: muse-ember-1.0muse-ember-1.0Request example
muse-ember-1.0.Gotchas
- Use provider model ID "muse-ember-1.0", not the LLMReference slug "muse-ember".
Compare Muse Ember Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Meta Model API | $0.10 | $0.50 |
| OpenRouter | $0.10 | $0.50 |
| Vercel AI Gateway | $0.10 | $0.50 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
| Output tokens | $0.50 |
Capabilities
About Muse Ember
Muse Ember is Meta Superintelligence Labs' smallest and most efficient Muse model, introduced November 9, 2026, for the work agents repeat all day: tool calls, coding subtasks, routing, extraction and long-document parsing. Meta says it is the first model trained using Muse Wonder Full. It takes text, image, audio and video input and returns text, with a 1M-token context window and up to 512K output tokens, and supports the Responses API.