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 | Fugu Ultrafugu-ultra | Hy4 previewhy4-preview |
|---|---|---|
| Pricing | ||
| Input | $5.00 / 1M | $0.834 / 1M |
| Output | $30.00 / 1M | $2.50 / 1M |
| Cache Write (5m) | $5.00 / 1M | $0.834 / 1M |
| Cache Write (1h) | $5.00 / 1M | $0.834 / 1M |
| Cache Read | $5.00 / 1M | $0.834 / 1M |
| Web Search | $0 / 1M | $0 / 1M |
| Context | ||
| Max context | 1M | 1M |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | Yes | Yes |
| Function Calling | Yes | Yes |
| JSON Mode | Yes | Yes |
| Streaming | Yes | Yes |
| Catalogue | ||
| Provider | Sakana | Tencent |
| Category | chat | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | Fugu Ultra is the high-performance model in Sakana AI's Fugu family, built as a learned multi-agent orchestration system rather than a single monolithic model. It intelligently routes tasks across a pool of underlying models and can recursively invoke itself to solve complex problems more effectively. Optimized for multi-step reasoning, coding, and agentic workflows, Fugu Ultra supports configurable reasoning effort, native tool calling, and built-in web search. Its orchestration-based design makes it well suited for advanced autonomous agents and complex task execution requiring adaptive model coordination. | 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. |