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 | Tongyi DeepResearch 30B A3Btongyi-deepresearch-30b-a3b | Muse Spark Openmuse-spark-open |
|---|---|---|
| Pricing | ||
| Input | $0.135 / 1M | $1.25 / 1M |
| Output | $0.675 / 1M | $4.25 / 1M |
| Cache Write (5m) | $0.135 / 1M | $1.25 / 1M |
| Cache Write (1h) | $0.135 / 1M | $1.25 / 1M |
| Cache Read | $0.135 / 1M | $1.25 / 1M |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 131.1K | 1M |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | No | Yes |
| Function Calling | Yes | Yes |
| JSON Mode | Yes | Yes |
| Streaming | Yes | Yes |
| Catalogue | ||
| Provider | Alibaba | Meta |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | Tongyi DeepResearch is a 30B-parameter agentic model (3B active per token) built for long-horizon, deep research and information-seeking tasks. It achieves state-of-the-art results on major agentic search and reasoning benchmarks, outperforming prior models in complex multi-step problem solving. Trained with a fully automated synthetic data pipeline and advanced on-policy RL, it supports ReAct workflows and a high-performance “Heavy” mode for test-time scaling, making it well suited for advanced research agents, tool use, and intensive inference workloads. | Muse Spark Open is an open-weight, coding-optimized model designed for agentic software engineering workflows. It delivers strong first-attempt accuracy, reliable tool calling, and deep codebase understanding, enabling effective development across real-world repositories. Optimized for autonomous coding agents, complex code navigation, and tool-driven development, Muse Spark Open is well suited for software engineering automation, debugging, code generation, and multi-step coding workflows where accuracy and reliable execution are essential. |