Scan to join WeChat groupKimi K2 Thinking Turbo
Kimi K2 Thinking Turbo: a kimi-thinking model from Moonshot AI, ~262.1K context, knowledge cutoff 2024-08
Kimi K2 Thinking Turbo is a kimi-thinking model from Moonshot AI (~262.1K context, input around $1.15/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation
starsCapabilities
codeFunction calling
paymentsContext and pricing
Context limit262,144
Max output262,144
Knowledge cutoff2024-08
Input price$1.15/ 1M tokens
Output price$8/ 1M tokens
Cached input price$0.15/ 1M tokens
descriptionOverview
Overview
Kimi K2 Thinking Turbo is provided by Moonshot AI, model ID kimi-k2-thinking-turbo
Key specs
- Context: 262.1K tokens
- Max output: 262.1K tokens
- Knowledge cutoff: 2024-08
- Input price: $1.15/1M
- Output price: $8/1M
Best for
Consider Kimi K2 Thinking Turbo when comparing context length, pricing, multimodal support and relay availability
lightbulbUse cases
- Assistants and customer support
- Content generation and rewriting
- Knowledge Q&A and summarization
- Structured extraction
thumb_upStrengths
- Very long context (~262.1K), good for long documents and codebases
- Open weights, can be self-hosted
- High single-response output limit (~262.1K)
infoLimitations
- Knowledge cutoff 2024-08; newer facts need external retrieval
- Pricing and availability vary by upstream and relay; verify with official docs and tests