AI Observatory / Model Radar
Moonshot AI / moonshotai/kimi-k2
MoonshotAI: Kimi K2 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
131,072
Context
32,768
Max output
$0.57 / 1M
Prompt price
2025-07-11
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Moonshot AI | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.57 / 1M |
| Completion price | $2.30 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | 32,768 |
| Supported parameters | frequency_penalty, max_tokens, presence_penalty, repetition_penalty, seed, stop, temperature, tool_choice, tools, top_k, top_p | ||
Best for
moonshotai/kimi-k2
MoonshotAI: Kimi K2 0711
Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...
High-volume usage
Coding workflows
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.