# EP 38: What Is Meta Muse Ember? The Tiny Model Built for Agent Tasks - URL: https://www.agenticpod.net/episodes/ep38-meta-muse-ember/ - Watch on YouTube: https://www.youtube.com/watch?v=tT9CMKiMucI - Published: 2026-11-11 - Length: 5 min - Hosts: Stella (asks), Liam (answers). Both are AI hosts with AI-generated voices. ## Summary Meta Superintelligence Labs just launched Muse Ember, its smallest and most efficient model, built for the repetitive work inside agent runs. ## Key takeaways - Muse Ember is Meta's smallest and most efficient model, built for the repetitive work inside agent runs: tool calls, routing, extraction, long document processing and coding subtasks. - It costs $0.10 per million input tokens, $0.004 cached input and $0.50 output, with up to 1M tokens of context and 512K tokens of output. - It matches Claude Haiku on the Intelligence Index (36) at about one third of the cost per task, but loses on FrontierCode, 27.2 vs 34.9, and it is not open weights. - The winning pattern is a planner plus Ember: a bigger model plans and checks, Ember does the volume legwork through the Meta Model API (muse-ember-1.0), Muse Code, Google Cloud or Oracle Cloud. ## Chapters - 0:00 Intro - 0:40 What Muse Ember is and why it matters - 1:36 The numbers: pricing, context and benchmarks - 3:08 How to try it and a real workflow - 4:22 Gotchas, who it is for, and the verdict ## FAQ **What is Meta Muse Ember?** The smallest model in Meta Superintelligence Labs' Muse family, launched November 9, 2026, tuned for repetitive agent subtasks like tool calls, routing, extraction and small coding jobs. **How much does Muse Ember cost?** $0.10 per million input tokens, $0.004 per million cached input tokens, and $0.50 per million output tokens, with up to 1M tokens in and 512K tokens out. **Is Muse Ember open weights?** No. It is available through the Meta Model API, Muse Code, Google Cloud and Oracle Cloud. ## Resources - [Step-by-step guide](https://github.com/asly-97/ai-automation-workflows/tree/main/meta-muse-ember-agent-model) - [Meta Superintelligence Labs Muse Ember announcement, November 9 2026](https://lapaasvoice.com) ## Transcript ### Intro Liam: Hey hey hey, welcome to Agentic Pod! I'm Liam. Stella: And I'm Stella! Liam, Meta just launched a model that costs 10 cents per million input tokens? Liam: Ten cents. That is Muse Ember, from Meta Superintelligence Labs. It launched on November 9th, and it is built for one job. Repetitive agent work. Stella: Ten cents sounds like a typo. Is it actually smart? Liam: That is the whole question. By the end you will know the price, the benchmarks, where it loses, and how to try it today. ### What Muse Ember is and why it matters Stella: Okay, start simple. What is Ember, in one sentence? Liam: It is the smallest model in Meta's Muse family. Muse Wonder does the planning. Muse Ember handles the volume. Stella: So the big brain thinks, and the small one does the chores? Liam: Exactly. Tool calls. Routing. Pulling facts from documents. Reading files. Running tests. One small targeted code change. Stella: The boring steps that fill every agent run. Liam: And they add up fast. One task can mean hundreds of small calls. If every call uses a huge model, the bill explodes. Liam: Ember is also multimodal. Text, image, audio and video. It can read a screenshot or a long document, not just plain text. Stella: Okay, that is useful. But cheap and useful rarely travel together. Show me the numbers. ### The numbers: pricing, context and benchmarks Liam: Pricing first. 10 cents per million input tokens. Cached input is almost free, at $0.004 per million. Output is 50 cents per million. Stella: Wait, say the context size. That part surprised me. Liam: Up to one million tokens in. And up to 512,000 tokens out. That is a huge window for a tiny model. Stella: So it can swallow a whole code base in one go. Liam: That is the idea. Now the scores. On the Artificial Analysis Intelligence Index, Ember scores 36 at max reasoning. Stella: And the comparison everyone will ask about? Liam: Claude Haiku also scores 36. But Ember costs about 14 cents per task, against 41 cents for Haiku. Roughly one third the cost. Stella: One third. Okay, that got my attention. Liam: On Automation Bench, Ember scores 37.8, against 13.9 for Haiku. On the Coding Agent Index, 46 against 37. Stella: Those are big gaps. Where does it lose? Be honest. Liam: I will. On Frontier Code, Ember scores 27.2, and Haiku scores 34.9. Ember does not win everywhere. Stella: Good, you said it out loud. A chart that only shows wins is just an ad. Liam: Terminal-Bench is close too. Ember 40.9, Haiku 39.2. So how do you actually try it? ### How to try it and a real workflow Stella: Yes, step by step. Where do I even get it? Liam: Step one, go to the Meta Model API. The model ID is muse-ember-1.0. It works through the Responses API. Stella: And if I live in a coding tool all day? Liam: Step two, try Muse Code. Step three, it is also on Google Cloud and Oracle Cloud. Stella: And real teams are already using it? Liam: Meta lists Box, Cline, Oracle, Cloudflare and You.com. Cloudflare reports up to 30% faster tail latency. You.com reports 2.2 second 95th percentile latency, and finished all its coding quests. Stella: Okay, give me one real workflow, not a feature list. Liam: Here is mine. Your big model plans the feature and writes the spec. Then Ember does the volume work underneath it. Stella: Like what, concretely? Liam: Ember reads the twenty files the plan touches. It runs the tests after each change. It pulls the exact lines you need from a long doc. The planner only wakes up for real decisions. Stella: So I pay planner prices for decisions, and Ember prices for legwork. Liam: Exactly. But there are catches, and one of them matters a lot. ### Gotchas, who it is for, and the verdict Stella: Let me guess the first catch. It is not open weights? Liam: Correct. Not open weights. You call it through Meta or a cloud partner. If you need a model you can run yourself, this is not that. Stella: Catch two is the FrontierCode score you already confessed. Liam: Confessed is fair. For the hardest coding work, a bigger model still wins some rounds. Ember is a volume tool, not a genius replacement. Stella: So who should actually try it this week? Liam: Anyone whose agent bill is mostly small calls. Routing, extraction, tool calls, test runs, first pass code edits. That is Ember's home turf. Stella: And who should skip it? Liam: Anyone who needs open weights, or anyone whose work is one hard problem at a time. You will not feel the savings there. Stella: My verdict: the price is the story. 14 cents a task changes what you can afford to automate. Liam: Same. The guide with the API steps is in the description. Would you let a tiny model run your agent's busywork? Tell us in the comments. See you next time!