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 | GPT OSS 20Bgpt-oss-20b | GLM 5.3 Flashglm-5.3-flash | Muse Spark 1.3muse-spark-1.3 |
|---|---|---|---|
| Pricing | |||
| Input | $0.075 / 1M | $0.075 / 1M | $1.25 / 1M |
| Output | $3.00 / 1M | $0.25 / 1M | $4.25 / 1M |
| Cache Write (5m) | $0.075 / 1M | $0.075 / 1M | $1.25 / 1M |
| Cache Write (1h) | $0.075 / 1M | $0.075 / 1M | $1.25 / 1M |
| Cache Read | $0.075 / 1M | $0.075 / 1M | $1.25 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | |||
| Max context | 131.1K | 1M | 1M |
| Max output | N/A | N/A | N/A |
| Capabilities | |||
| Vision | No | Yes | Yes |
| Function Calling | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes |
| Catalogue | |||
| Provider | OpenAI | Z.AI | Meta |
| Category | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — |
| Description | |||
| Summary | gpt-oss-20b is an open-weight, 21B-parameter OpenAI model released under Apache 2.0. It uses a Mixture-of-Experts design so only ~3.6B parameters run each step, enabling faster, lower-cost inference on consumer or single-GPU hardware. Trained in the Harmony format, it supports configurable reasoning depth, fine-tuning, function calling, tool use, and structured outputs. | 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. | Muse Spark 1.3 is Meta's multimodal reasoning model designed for long-running agentic, multi-agent, and coding workflows. It maintains context and information across extended tasks, enabling reliable execution in complex, multi-step environments. The model is optimized to resolve conflicting information, seek clarification or confirmation when necessary, and execute concisely, making it well suited for autonomous agents, collaborative multi-agent systems, and long-horizon software engineering workflows. |