Muse Ember from Meta is an efficient reasoning model built for high-volume agent tasks, including tool calls, coding subtasks, routing, extraction, and long-document processing. It accepts text and image inputs with a 1M-token context window and up to 524,288 output tokens. Pair it with Muse Wonder or Muse Spark 1.3 for multi-step planning and reasoning.
Requests on the global /locations/global/publishers/meta/v1/responses endpoint
pass the bare model ID muse-ember-1.0 in the model
field. For an example request, see
Use Meta models.
View model card in Model Garden
| Model ID | meta/muse-ember-1.0 |
|
|---|---|---|
| Launch stage | Preview | |
| Supported inputs & outputs |
|
|
| Token limits |
|
|
| Capabilities |
|
|
| Usage types |
|
|
| Versions |
|
|
| Supported regions | ||
|
Model availability |
|
|
| Quota limits |
global endpoint:
|
|
| Pricing | See Pricing. | |
Inference parameters and limitations
Keep the following inference parameters and limitations in mind when sending requests:
- Reasoning effort: Set
reasoning.efforttominimal,low,medium,high,xhigh, ormax(usexhighormaxfor agentic and coding work).noneisn't supported. Pricing is the same at every effort level. - Reasoning output: Reasoning content is returned in encrypted form for multi-turn replay. Reasoning summaries are returned at higher effort levels and might be absent at lower ones.
- Tool calling: Supports built-in tool calling with Model Context Protocol
(MCP) support.
tool_choicesupportsautoonly (none,required, and named-function choices aren't supported). - Recommended sampling:
temperature1.0,top_p1.0(top_kdisabled). - Recommended pairing: Pair Muse Ember with Muse Wonder for complex open-ended coding, or use retrieval for knowledge-heavy recall.
- Known limitations: Audio, video, and PDF inputs, chat completions, and
stateful response storage (
store: true) aren't supported. For the full capability list, see the table earlier on this page.
What's next
- Send requests using Use Meta models.
- View Muse Ember on Google Cloud Marketplace.
- Explore the Meta Model API documentation.
- Review the Meta Model API Terms of Service and Acceptable Use Policy, which apply alongside the Google Cloud Marketplace Terms of Service.