Moonshot AI
Chinese AI company focused on large language models. Requesty routes to 7 Moonshot AI models starting at $0.60 per 1M input tokens with context windows up to 262K tokens. One API key, OpenAI-compatible SDK, no markup.
All Moonshot AI models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
kimi-k2.6 | 262K | 262K | $0.95 | $4.00 | 👁🧠🔧⚡ | — |
kimi-k2.5 | 262K | 262K | $0.60 | $3.00 | 👁🧠🔧⚡ | — |
kimi-k2-thinking-turbo | 131K | — | $0.60 | $2.50 | 🔧 | — |
kimi-k2-0905-preview | 131K | — | $0.60 | $2.50 | 🔧 | — |
kimi-k2-thinking | 131K | — | $0.60 | $2.50 | 🔧 | — |
kimi-k2-turbo-preview | 131K | — | $1.20 | $5.00 | 🔧 | — |
kimi-k2-0711-preview | 131K | — | $0.60 | $2.50 | 🔧 | — |
About Moonshot AI on Requesty
How many Moonshot AI models are available through Requesty?
Requesty routes to 7 Moonshot AI models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Moonshot AI model?
The cheapest Moonshot AI model starts at $0.60 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Moonshot AI pricing?
No. Requesty passes through exactly what Moonshot AI charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Moonshot AI models?
Moonshot AI's training policy varies by product and tier. See their privacy policy for specifics, and contact Requesty for enterprise-grade data controls.
Where are Moonshot AI models hosted?
Moonshot AI models are hosted in 🇨🇳 China. Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Moonshot AI rows in the models explorer.