Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.Muse Wonder Full by meta is currently listed from a single provider. No official API price is listed for it; the prices below come from third-party channels.
Artificial Analysis rates it 50.1 on the Intelligence Index, with 57.9 for Strategy & Ops, its strongest domain. Against its lowest blended price of $9.60 per 1M, that is roughly 5 index points per dollar, which is the value ratio the leaderboards rank on.
The context window is 1,048,576 tokens, with an output limit of 131,072 tokens. It supports reasoning and tool use. Accepted input modalities are Image, PDF, and Text.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari muse-wonder-full-1-0 | Gateway | $4.80 | $24.00 | $0.24 | — | 1,048,576 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-17). Each future sync adds a point, and once accumulated a line is drawn here.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Harvey Legal Agent Benchmark | variant: max effort; Artificial Analysis LAB-AA · v1.1 | 13.1 | all-pass rate | Source ↗ |
| Finance Agent | variant: max effort · dataset: Vals AI private test set · vv2 | 59.1 | accuracy | Source ↗ |
| HealthBench Professional | variant: max effort | 62.3 | length-normalized weighted rubric score | Source ↗ |
| AutomationBench | variant: max effort; Artificial Analysis AutomationBench-AA | 45.4 | strict pass@1 | Source ↗ |
| GDP.pdf | variant: max effort | 33.2 | score | Source ↗ |
| JobBench | variant: max effort | 75.3 | mean reward | Source ↗ |
| OSWorld | variant: max effort · v2.1 | 78.4 | mean partial score | Source ↗ |
| OSWorld | variant: max effort · v2.1 | 39.4 | binary completion rate | Source ↗ |
| Terminal-Bench | variant: max effort; Artificial Analysis Terminal-Bench 4.0-AA · v4.0 | 57.1 | accuracy | Source ↗ |
| DeepSWE | variant: max effort · v1.1 | 79 | pass@1 | Source ↗ |
| SWE-Marathon | variant: xhigh effort | 57.5 | pass@1 | Source ↗ |
| ProgramBench | harness: mini-swe-agent · variant: max effort | 59 | share of rollouts passing at least 95% of tests | Source ↗ |
| Artificial Analysis Intelligence Index | variant: max effort · v4.3 | 56 | index score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.