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.
- Mistral Embed 2312Mistral AIRemove
- GPT-6 Astra ProOpenAIRemove
- GLM 5.3Z.AIRemove
- Hy4 previewTencentRemove
4 is the maximum. Remove one to add another.
| Attribute | Mistral Embed 2312mistral-embed-2312 | GPT-6 Astra Progpt-6-astra-pro | GLM 5.3glm-5.3 | Hy4 previewhy4-preview |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.125 / 1M | $10.00 / 1M | $1.40 / 1M | $0.834 / 1M |
| Output | $0 / 1M | $50.00 / 1M | $4.40 / 1M | $2.50 / 1M |
| Cache Write (5m) | $0.125 / 1M | $10.00 / 1M | $1.40 / 1M | $0.834 / 1M |
| Cache Write (1h) | $0.125 / 1M | $10.00 / 1M | $1.40 / 1M | $0.834 / 1M |
| Cache Read | $0.125 / 1M | $10.00 / 1M | $1.40 / 1M | $0.834 / 1M |
| Web Search | — | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 8.2K | 1M | 1M | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | No | Yes | No | Yes |
| Function Calling | No | Yes | Yes | Yes |
| JSON Mode | No | Yes | Yes | Yes |
| Streaming | No | Yes | Yes | Yes |
| Catalogue | ||||
| Provider | Mistral AI | OpenAI | Z.AI | Tencent |
| Category | embedding | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | 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. | GPT-6 Astra Pro uses the same underlying model as GPT-6 Astra, but runs with reasoning.mode set to pro for higher-quality responses on complex tasks. Optimized for deeper reasoning, greater accuracy, and more reliable multi-step execution, it is well suited for demanding coding, analysis, and agentic workflows where solution quality takes priority over speed and cost. | GLM-5.3 is Z.ai's large-scale reasoning model designed for complex software engineering and long-horizon agentic workflows. It supports text input and output with a 1M-token context window, enabling sustained reasoning across large codebases and extended multi-step tasks. Building on GLM-5.2, it delivers stronger coding performance while improving the balance between capability and token efficiency, making it well suited for autonomous coding agents, large-scale engineering workflows, and complex task execution. | 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. |