What a 1,000-step agent run costs on Meta's new Muse Ember ($0.10 / $0.50 per 1M tokens)

Disclosure: this post contains an affiliate link to Hostinger; I may earn a commission at no cost to you.

TL;DR: Meta released Muse Ember on Nov 10, 2026, a small model aimed at the repetitive steps in agent loops (read a file, run a test, extract a field, call a tool). At $0.10 input, $0.004 cached input and $0.50 output per 1M tokens, a 1,000-step loop costs cents. Below: the math, a copy-paste cost calculator, and a routing rule for when to escalate to a bigger model.

Prices (as published Nov 9-10, 2026)

Sources: VentureBeat and Gadgets360 on Muse Ember; andrew.ooo price table for GPT-6.1 Terra. Anthropic also announced Claude Fable 5.2 / Mythos 5.2 with a 20% API cost cut, so check your frontier tier too.

Worked example

Assumptions (mine, change them): each step sends 6,000 input tokens, of which 5,000 are a cached prefix, and returns 300 output tokens.

def run_cost(steps, in_tok, cached_tok, out_tok, p_in, p_cached, p_out): fresh = in_tok - cached_tok per_step = (fresh*p_in + cached_tok*p_cached + out_tok*p_out) / 1e6 return steps * per_step ember = run_cost(1000, 6000, 5000, 300, 0.10, 0.004, 0.50) terra = run_cost(1000, 6000, 0, 300, 1.00, 1.00, 5.00) # no cache discount assumed print(f"Ember ${ember:.3f} Terra ${terra:.2f}") 

Result: about $0.27 on Ember vs $7.50 on Terra per 1,000 steps (Terra without caching, so this flatters Ember; with caching the gap narrows but stays large).

Routing rule: cheap by default, escalate on failure

CHEAP, BIG = "muse-ember-1.0", "your-frontier-model" def pick(task): if task.kind in {"read","extract","run_tests","tool_call"} and task.retries == 0: return CHEAP return BIG # planning, failed retries, ambiguous specs 

Log retries per task type for a week; if Ember's retry rate on a step type exceeds ~20%, move that type to the bigger model.

Where to run it

A router like this is a tiny always-on process. A small VPS is enough; I use Hostinger for this kind of thing: Hostinger VPS. Keep API keys in env vars, not in the repo.

Decision table

Full disclosure: some links in this article are affiliate links. If you buy through them, TokenLean may earn a commission at no extra cost to you. Prices change; verify on the vendor pages before relying on them.