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 | Gemini 2.5 Flash Litegemini-2.5-flash-lite | Claude Fable 5.1claude-fable-5.1 | Hy4 previewhy4-preview |
|---|---|---|---|
| Pricing | |||
| Input | $0.15 / 1M | $10.00 / 1M | $0.834 / 1M |
| Output | $0.60 / 1M | $50.00 / 1M | $2.50 / 1M |
| Cache Write (5m) | $0.15 / 1M | $12.50 / 1M | $0.834 / 1M |
| Cache Write (1h) | $0.15 / 1M | $20.00 / 1M | $0.834 / 1M |
| Cache Read | $0.15 / 1M | $1.00 / 1M | $0.834 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1.0M | 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 | Anthropic | Tencent | |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | Gemini 2.5 Flash-Lite is a smaller, low-latency model focused on speed and cost efficiency. It delivers faster generation and better benchmark performance than earlier Flash models. Thinking mode is off by default for maximum speed, but developers can enable it when they want deeper reasoning at a higher cost. | Claude Fable 5.1 is an upgraded version of Fable 5, delivering broad improvements with particularly strong gains in agentic coding, long-running workflows, and professional knowledge work. It excels at large code refactors, front-end and visual code generation, financial analysis, and complex analytical tasks. Compared with Fable 5, it also produces more concise plans and summaries while maintaining strong performance across extended tasks, making it a natural upgrade for existing Fable workflows and a strong option alongside Opus 5 for reasoning-intensive applications. | 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. |