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 | GLM 5.3 Flashglm-5.3-flash | Gemini 3.8 Flashgemini-3.8-flash | GPT OSS 120Bgpt-oss-120b |
|---|---|---|---|
| Pricing | |||
| Input | $0.075 / 1M | $0.75 / 1M | $0.15 / 1M |
| Output | $0.25 / 1M | $3.75 / 1M | $0.75 / 1M |
| Cache Write (5m) | $0.075 / 1M | $0.75 / 1M | $0.15 / 1M |
| Cache Write (1h) | $0.075 / 1M | $0.75 / 1M | $0.15 / 1M |
| Cache Read | $0.075 / 1M | $0.75 / 1M | $0.15 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 1M | 1M | 131.1K |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | Yes | Yes | No |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | Z.AI | OpenAI | |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | 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. | Gemini 3.8 Flash is Google's most intelligent Flash-class model, delivering significant improvements over Gemini 3.7 Flash across software engineering, agentic workflows, and complex multi-step reasoning. Designed to combine strong capability with Flash-tier efficiency, it is well suited for coding assistants, autonomous agents, and high-throughput production workflows that require responsive performance without sacrificing reasoning quality. | gpt-oss-120b is an open-weight 117B-parameter MoE model from OpenAI, built for advanced reasoning and production workloads. Only about 5.1B parameters are active per step, and it’s optimized to run on a single H100 using MXFP4 quantization. It supports adjustable reasoning depth, full chain-of-thought, and native agent features like tool use, function calling, browsing, and structured outputs. |