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.
- GLM-4Z.AIRemove
- Muse Spark 1.3MetaRemove
- DeepSeek V4.1 FlashDeepSeekRemove
- Gemini 3.8 FlashGoogleRemove
4 is the maximum. Remove one to add another.
| Attribute | GLM-4glm-4 | Muse Spark 1.3muse-spark-1.3 | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Gemini 3.8 Flashgemini-3.8-flash |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.21 / 1M | $1.25 / 1M | $0.30 / 1M | $0.75 / 1M |
| Output | $0.21 / 1M | $4.25 / 1M | $1.20 / 1M | $3.75 / 1M |
| Cache Write (5m) | $0.21 / 1M | $1.25 / 1M | $0.30 / 1M | $0.75 / 1M |
| Cache Write (1h) | $0.21 / 1M | $1.25 / 1M | $0.30 / 1M | $0.75 / 1M |
| Cache Read | $0.21 / 1M | $1.25 / 1M | $0.30 / 1M | $0.75 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 128K | 1M | 1M | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | Yes | Yes | Yes | Yes |
| Function Calling | Yes | Yes | Yes | Yes |
| JSON Mode | Yes | Yes | Yes | Yes |
| Streaming | Yes | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | Z.AI | Meta | DeepSeek | |
| 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 | GLM-4V-9B is the open-source multimodal model in Zhipu AI’s GLM-4 series. It supports high-resolution (1120×1120) bilingual Chinese–English dialogue across multiple turns, and performs strongly in perception, reasoning, OCR, and chart understanding. Across many multimodal benchmarks, it outperforms models such as GPT-4-turbo-2024-04-09, Gemini 1.0 Pro, Qwen-VL-Max, and Claude 3 Opus. | 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. | 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. | 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. |