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 | Hy4 previewhy4-preview | DeepSeek V4.1 Flashdeepseek-v4.1-flash |
|---|---|---|---|
| Pricing | |||
| Input | $0.15 / 1M | $0.834 / 1M | $0.30 / 1M |
| Output | $0.60 / 1M | $2.50 / 1M | $1.20 / 1M |
| Cache Write (5m) | $0.15 / 1M | $0.834 / 1M | $0.30 / 1M |
| Cache Write (1h) | $0.15 / 1M | $0.834 / 1M | $0.30 / 1M |
| Cache Read | $0.15 / 1M | $0.834 / 1M | $0.30 / 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 | Tencent | DeepSeek | |
| 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. | 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. | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. |