Moonshot: Kimi K2 Thinking
moonshotai/kimi-k2-thinking
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 Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
Model specifications
- Input
- text
- Output
- text
- Context
- 262,144 tokens
- Max output
- 262,144 tokens
- Input price
- $0.6 / 1M tokens
- Output price
- $3 / 1M tokens
- Released
- 2026-02-10
Capabilities
- Streaming
- Function calling
- JSON mode
- Playground
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $0.6 / 1M tokens · tier output average $2.5 / 1M tokens
AtlasCloud
Tier: Standard · Region: US
Pricing
- Input
- $0.6 / 1M tokens
- Output
- $2.5 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Data retention
- 7-day retention
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Privacy policy · Terms · Official website · Documentation · Support
Frequently asked questions
- What is Moonshot: Kimi K2 Thinking?
- 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 Kimi K2, it activates 32 billion parameters per forward pass and supports 256 k-token context windows. The model is optimized for persistent step-by-step thought, dynamic tool invocation, and complex reasoning workflows that span hundreds of turns. It interleaves step-by-step reasoning with tool use, enabling autonomous research, coding, and writing that can persist for hundreds of sequential actions without drift. It sets new open-source benchmarks on HLE, BrowseComp, SWE-Multilingual, and LiveCodeBench, while maintaining stable multi-agent behavior through 200–300 tool calls. Built on a large-scale MoE architecture with MuonClip optimization, it combines strong reasoning depth with high inference efficiency for demanding agentic and analytical tasks.
- How much does Moonshot: Kimi K2 Thinking cost?
- Input costs start at $0.6 / 1M tokens and output costs start at $3 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Moonshot: Kimi K2 Thinking?
- Moonshot: Kimi K2 Thinking supports a 262,144 token context window and up to 262,144 output tokens.
- What capabilities does Moonshot: Kimi K2 Thinking support?
- Moonshot: Kimi K2 Thinking supports Streaming, Function calling, JSON mode, Playground.
- Which providers offer Moonshot: Kimi K2 Thinking?
- Moonshot: Kimi K2 Thinking is available from AtlasCloud.
- How do providers handle data privacy for Moonshot: Kimi K2 Thinking?
- 1 of 1 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.