Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
| Attribute | Muse Wondermuse-wonder | ERNIE 4.5 21B A3B Thinkingernie-4.5-21b-a3b-thinking |
|---|---|---|
| Pricing | ||
| Input | $4.00 / 1M | $0.035 / 1M |
| Output | $20.00 / 1M | $0.14 / 1M |
| Cache Write (5m) | $4.00 / 1M | $0.035 / 1M |
| Cache Write (1h) | $4.00 / 1M | $0.035 / 1M |
| Cache Read | $4.00 / 1M | $0.035 / 1M |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 1M | 131.1K |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | Yes | Yes |
| Function Calling | Yes | Yes |
| JSON Mode | Yes | Yes |
| Streaming | Yes | Yes |
| Catalogue | ||
| Provider | Meta | Baidu |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | Muse Wonder is Meta’s frontier multimodal reasoning model, designed for complex personal and professional agentic workflows. It supports text, image, video, audio, and PDF inputs with text output and features a 1M-token context window for sustained reasoning across long-running tasks. Optimized for autonomous execution and multi-agent orchestration, Muse Wonder can plan, delegate to subagents, coordinate parallel tool use, recover from errors, and operate browsers and applications across desktop and mobile environments. With cross-conversation context retrieval and its Active Focus training approach, it is well suited for complex software engineering, multi-file refactoring, computer use, and end-to-end workflows requiring persistence, adaptability, and minimal supervision. | ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model focused on deeper, higher-quality reasoning. It's tuned to perform strongly on logic, math, science, coding, text generation, and advanced academic benchmarks, delivering top-tier capability with efficient compute usage. |