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.
4 is the maximum. Remove one to add another.
| Attribute | ERNIE Speed 128KERNIE-Speed-128K | Hy4 previewhy4-preview | Qwen3.8 27Bqwen3.8-27b | GLM 5.3 Flashglm-5.3-flash |
|---|---|---|---|---|
| Pricing | ||||
| Input | $1.46 / 1M | $0.834 / 1M | $0.45 / 1M | $0.075 / 1M |
| Output | $2.92 / 1M | $2.50 / 1M | $3.20 / 1M | $0.25 / 1M |
| Cache Write (5m) | $1.457 / 1M | $0.834 / 1M | $0.45 / 1M | $0.075 / 1M |
| Cache Write (1h) | $1.457 / 1M | $0.834 / 1M | $0.45 / 1M | $0.075 / 1M |
| Cache Read | $1.457 / 1M | $0.834 / 1M | $0.45 / 1M | $0.075 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 131.1K | 1M | 262K | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | Yes | Yes | Yes |
| Function Calling | No | Yes | Yes | Yes |
| JSON Mode | No | Yes | Yes | Yes |
| Streaming | No | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | Baidu | Tencent | Alibaba | Z.AI |
| Category | chat | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | 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. | Qwen3.8 27B is an open-weight dense vision-language model from Qwen, designed for coding, professional knowledge work, research, and multimodal interaction. It combines strong text and visual understanding with capabilities optimized for sustained, real-world agentic tasks. The model supports flexible thinking modes that can be enabled for deeper reasoning or disabled for faster execution, making it well suited for long-running agents, multimodal workflows, coding assistants, and cost-conscious self-hosted deployments. | 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. |