Kimi K2 Thinking
Provider：Moonshot AI
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Key specs
- Context：262.1K
- Max output：100.4K
- Tokenizer：Other
- Released：2025-11-06
Token pricing
- Input price：$0.600 / 1M tokens
- Output price：$2.50 / 1M tokens
- Cache read：$0.150 / 1M tokens
- Blended price：$1.07 / 1M tokens
Modalities
Text
Use Cases
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（≈ $0.020/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0050/call）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
FAQ
- What is the token pricing of Kimi K2 Thinking? Input price $0.600 / 1M tokens, output price $2.50 / 1M tokens, blended about $1.07 / 1M tokens. Refer to Moonshot AI’s official page for the exact rate.
- What context window does Kimi K2 Thinking support? Context window is 262.1K, max output about 100.4K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Kimi K2 Thinking best for? Based on its capability and pricing, Kimi K2 Thinking fits best: Deep Reasoning & Analysis, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Kimi K2 Thinking support? Supports Text modality.
- Is Kimi K2 Thinking a free model? Kimi K2 Thinking is billed per token, not a free model.
- Which provider offers Kimi K2 Thinking? Kimi K2 Thinking is offered by Moonshot AI.
More models from Moonshot AI
Full info：Kimi K2 Thinking