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 | Mistral Embed 2312mistral-embed-2312 | GLM 5.3 Flashglm-5.3-flash |
|---|---|---|
| Pricing | ||
| Input | $0.125 / 1M | $0.075 / 1M |
| Output | $0 / 1M | $0.25 / 1M |
| Cache Write (5m) | $0.125 / 1M | $0.075 / 1M |
| Cache Write (1h) | $0.125 / 1M | $0.075 / 1M |
| Cache Read | $0.125 / 1M | $0.075 / 1M |
| Web Search | — | $0 / 1M |
| Context | ||
| Max context | 8.2K | 1M |
| Max output | N/A | N/A |
| Capabilities | ||
| Vision | No | Yes |
| Function Calling | No | Yes |
| JSON Mode | No | Yes |
| Streaming | No | Yes |
| Catalogue | ||
| Provider | Mistral AI | Z.AI |
| Category | embedding | chat |
| Charge type | Pay As You Go | Pay As You Go |
| Released | — | — |
| Description | ||
| Summary | Mistral Embed is Mistral AI's text embedding model, built for semantic search and RAG workflows. It generates 1024-dimensional vectors that capture meaningful relationships between pieces of text. | 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. |