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 | Nemotron 3.5 Super VL (Free)nemotron-3.5-super-vl:free | DeepSeek R1T Chimeradeepseek-r1t-chimera | Muse Spark Openmuse-spark-open |
|---|---|---|---|
| Pricing | |||
| Input | $0 / 1M | $0.30 / 1M | $1.25 / 1M |
| Output | $0 / 1M | $1.20 / 1M | $4.25 / 1M |
| Cache Write | $0 / 1M | — | — |
| Cache Read | $0 / 1M | $0.30 / 1M | $1.25 / 1M |
| Cache Write (5m) | — | $0.30 / 1M | $1.25 / 1M |
| Cache Write (1h) | — | $0.30 / 1M | $1.25 / 1M |
| Web Search | — | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1M | 163.8K | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | No | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | NVIDIA | TNG Tech | Meta |
| Category | chat | chat | chat |
| Charge type | Free | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | NVIDIA Nemotron 3.5 Super VL is an open multimodal Mixture-of-Experts (MoE) model featuring 120B total parameters with 12B activated per token. Built on a hybrid Mamba–Transformer architecture with multi-token prediction, it supports text, images, documents, GUI screenshots, and video inputs, along with a 1M-token context window for complex, long-horizon workflows. Optimized for multimodal reasoning, visual understanding, and agentic tool use, the model supports configurable reasoning modes and token budgets. It is well suited for document intelligence, web research, coding validation, customer service, GUI analysis, and video understanding, enabling efficient, long-running multimodal agent applications. | DeepSeek-R1T-Chimera combines DeepSeek-R1 with V3-0324 using a MoE architecture, blending R1’s reasoning strengths with V3's token efficiency. Optimized for general text generation and instruction following, it balances reasoning, efficiency, and usability. The model is MIT-licensed and available for both research and commercial use. | 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. |