# Muse Ember (slim)

> Muse Ember is Meta's smallest and most efficient hosted model, built for sub-agent tasks, tool calls, routing and work over large collections of files and images, taking text, images, video, audio and PDF with a 1M-token context.

- Full: https://www.anchorterminal.com/tools/muse-ember.md (~7,850 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/muse-ember.json · canonical https://www.anchorterminal.com/tools/muse-ember
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-09 · pricing https://www.anchorterminal.com/tools/muse-ember#pricing · reviews https://www.anchorterminal.com/tools/muse-ember#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**D · 51.8/100 · rank #1017 of 1515 · #36 in Model APIs & inference · not agent-ready · confidence medium** · same model listed separately: Meta Model API, Model API (https://www.anchorterminal.com/tools/meta-model-api.min.md)


Assessment: A cheap, capable model for the repeated parts of agent work, at $0.10 and $0.50 per million tokens with a 1M context and Meta's figures putting it level with Claude Haiku 5.5 on fewer tokens. Launched today on an API with no readable status page, SLA or deprecation policy, and closed, with no weights.

## Facts

- Kind: Model API · vendor: Meta · category: Model APIs & inference · legal entity: Meta Platforms, Inc. · provenance 64/100
- Endpoint: `https://api.meta.ai/v1` ()
- Auth: API key · pricing: Pay per use · x402: no · licence: Closed model, used through Meta Model API and Muse Code under the Meta Model API Terms of Service (last updated 9 October 2026). No open weights; Meta's open-weight models are Muse Spark Open and Muse Glimmer
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-09 20:50 UTC · uptime 30 days 100.0% (10 probes) · p50 48 ms · p95 72 ms over 24 hours
- Surface graded: The model as Meta Model API serves it, read from Meta's announcement, the developer launch post, the Muse Ember, models, choose-a-model and pricing pages on 9 November 2026. Platform readings (status, keys, retries, terms, data use, support) are the meta-model-api listing's of 12 October to 4 November. No account was made and nothing was called
- Model: Meta's smallest and most efficient model, natively multimodal, the first trained using Muse Wonder Full. Meta doesn't publish its parameter count or architecture
- Where it runs: Meta Model API in Standard mode only, as muse-ember-1.0, on the Responses, Chat Completions and Messages endpoints, and in Muse Code on pay-as-you-go and every plan
- Context: 1,048,576 tokens in, up to 524,288 out. Requests over 200K input tokens bill at the long-context rate for the whole request
- Pricing: Up to 200K input tokens, $0.10 input, $0.004 cached, $0.50 output per million. Over 200K, $0.30, $0.012 and $1.50. Muse Spark is $1.25 and $4.25, Muse Wonder $4.00 and $20.00. Claude Haiku 5.5 and GPT-6 Luna both list $0.10 and $0.50
- Meta's figures: Vendor-reported, at max reasoning. Artificial Analysis Intelligence Index 36 (Haiku 5.5 36, GPT-6 Luna 28), Coding Agent Index 46, Terminal-Bench 4.0 40.9%, AutomationBench 37.8%, FrontierCode 2.0 27.2% (Haiku 34.9%), OSWorld 2.1 69.5% partial credit. About $0.14 per Artificial Analysis task against $0.41 for Haiku. Agents' Last Exam, the Personal Superintelligence Index and PerceptionBench are internal
- Safety: Evaluated under Meta's Superintelligence Scaling Framework for chemical and biological, cyber and loss-of-control risk, below its high-risk thresholds per Meta, with agent tests for respecting intent, sensitive information, prompt injection and asking before high-impact actions
- Data use: Standard mode only, so content isn't used to train Meta models under the terms, per the meta-model-api listing's reading of 4 November
- Prices: Muse Ember input $0.10 per 1M tokens; Muse Ember cached input $0.004 per 1M tokens; Muse Ember output $0.50 per 1M tokens

- Scores: Reliability 40, Performance pending, Schema & documentation 60, Agent ergonomics 72, Security & auth 64, Payments & pricing 20, Task success pending, Maintenance & community 46, Transparency & trust 53 · total over the 7 assessed categories
- Why: Reliability, Model reading, for the surface it's called on, Meta Model API. · Schema & documentation, Model reading. · Agent ergonomics, Model reading. · Security & auth, Platform readings are the meta-model-api listing's of 4 November. · Payments & pricing, Published rubric. · Maintenance & community, Model reading. · Transparency & trust, Editorial half.
- Sources: 11, open questions: 5, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/muse-ember.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: https://dev.meta.ai/support/; https://dev.meta.ai/help; more in the full twin

## Before you call it

1. Call https://api.meta.ai/v1/responses (or /chat/completions or /messages) with model muse-ember-1.0 and a bearer MODEL_API_KEY
2. Set the effort explicitly, reasoning.effort on Responses or reasoning_effort on Chat Completions. It defaults to max, and none isn't accepted; minimal or low suits classification and routing
3. Keep input under 200K tokens a request, cached tokens and previous_response_id history included, or the whole request bills at the long-context rate
4. Use it for sub-agents and bounded repeated tasks, and a larger Muse model for the plan, as Meta advises
5. Use strict structured output for extraction and routing steps
6. In Claude Code, map the haiku alias and sub-agent model to muse-ember-1.0, per Meta's guide

## Connect

```bash
curl -X POST "https://api.meta.ai/v1/responses" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-ember-1.0",
  "input": "Classify this support ticket as billing, bug, or feature request.",
  "reasoning": {"effort": "low"}
}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Vertex AI (Gemini Enterprise Agent Platform) | AA | 88.7 | inference.llm | https://www.anchorterminal.com/tools/vertex-ai.min.md |
| OpenAI API | A | 83.9 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| Amazon Bedrock | A | 81.7 | inference.llm | https://www.anchorterminal.com/tools/amazon-bedrock.min.md |
| Azure OpenAI in Foundry Models | A | 80 | inference.llm | https://www.anchorterminal.com/tools/azure-openai.min.md |
| BlockRun.AI | A | 78.9 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)