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.
- Kimi K2 0711 Preview SearchMoonshot AIRemove
| Attribute | Kimi K2 0711 Preview Searchkimi-k2-0711-preview-search |
|---|---|
| Pricing | |
| Input | $0.165 / 1M |
| Output | $0.49 / 1M |
| Cache Write (5m) | $0.165 / 1M |
| Cache Write (1h) | $0.165 / 1M |
| Cache Read | $0.165 / 1M |
| Web Search | $0 / 1M |
| Context | |
| Max context | 63K |
| Max output | N/A |
| Capabilities | |
| Vision | Yes |
| Function Calling | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Catalogue | |
| Provider | Moonshot AI |
| Category | chat |
| Charge type | Pay As You Go |
| Released | — |
| Description | |
| Summary | Kimi K2 Instruct is a trillion-parameter MoE model from Moonshot AI, with 32B active parameters per step. Built for strong agentic behavior, it excels at tool use, reasoning, and code generation, leading major benchmarks in coding, logic, and tool-use tasks. It supports up to 128K context and uses a specialized training setup (including MuonClip) to stabilize very large MoE training. |