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 Ultranemotron-3-ultra-550b-a55b | Muse Spark 1.3muse-spark-1.3 | Hy4 previewhy4-preview |
|---|---|---|---|
| Pricing | |||
| Input | $0.50 / 1M | $1.25 / 1M | $0.834 / 1M |
| Output | $2.50 / 1M | $4.25 / 1M | $2.50 / 1M |
| Cache Write (5m) | $0.50 / 1M | $1.25 / 1M | $0.834 / 1M |
| Cache Write (1h) | $0.50 / 1M | $1.25 / 1M | $0.834 / 1M |
| Cache Read | $0.50 / 1M | $1.25 / 1M | $0.834 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1M | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | NVIDIA | Meta | Tencent |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | NVIDIA Nemotron 3 Ultra is an open frontier reasoning and orchestration model featuring a 550B-parameter Mixture-of-Experts (MoE) architecture with 55B active parameters per token. Built on a hybrid Transformer–Mamba design, it supports text input and output with a 1M-token context window, enabling large-scale reasoning and long-horizon task execution. Optimized for agent orchestration, coding agents, deep research, and complex enterprise workflows, the model excels at multi-step reasoning, planning, and sustained execution. With high-throughput inference designed for large-scale agent pipelines, Nemotron 3 Ultra serves as a powerful foundation for advanced agentic AI systems. | Muse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows. | Tencent Hy4 Preview is a Mixture-of-Experts (MoE) model from Tencent, featuring 770B total parameters with 49B activated per token. It is designed for coding agents, complex tool-driven workflows, and professional productivity tasks that require strong planning and reliable execution. Optimized for context continuity and sustained multi-step work, Hy4 Preview is well suited for long-horizon coding, agentic automation, tool orchestration, and complex real-world workflows. |