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 | Hy4 previewhy4-preview | Nemotron 3.5 Lightning (Free)nemotron-3.5-lightning:free | GLM 5.3 Flashglm-5.3-flash |
|---|---|---|---|
| Pricing | |||
| Input | $0.834 / 1M | $0 / 1M | $0.075 / 1M |
| Output | $2.50 / 1M | $0 / 1M | $0.25 / 1M |
| Cache Write (5m) | $0.834 / 1M | — | $0.075 / 1M |
| Cache Write (1h) | $0.834 / 1M | — | $0.075 / 1M |
| Cache Read | $0.834 / 1M | $0 / 1M | $0.075 / 1M |
| Web Search | $0 / 1M | — | $0 / 1M |
| Cache Write | — | $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 | Tencent | NVIDIA | Z.AI |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Free | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | 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. | NVIDIA Nemotron 3.5 Lightning is an open Mixture-of-Experts (MoE) model with 30B total parameters and 3B active per token, optimized for high-throughput agentic workloads and efficient inference. Its lightweight active compute and open design make it well suited for specialized agents, domain-specific customization, and scalable production deployments where speed, cost efficiency, and adaptability are key. | GLM-5.3-Flash is Z.AI's efficient native multimodal model, designed for coding and long-horizon agentic workflows. It combines strong multimodal capabilities with an architecture optimized for responsive, cost-efficient task execution. Built on a hybrid sparse and linear attention architecture, GLM-5.3-Flash maintains accurate long-context behavior while reducing computational overhead, making it well suited for coding agents, extended multi-step tasks, and scalable production workloads. |