Identity
- Status
- active
- Developer ID
moonshotai/Kimi-K2-Thinking- Released
- Nov 6, 2025
- Version
- Kimi-K2-Thinking
- License
- other
Moonshot AIKimi K2 Thinking
Kimi-K2-Thinking is an open-weight language model published by Moonshot AI.
- Token context
- 262K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Nov 6, 2025
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 OpenrouterAvailable | $0.60 | $2.50 | $0.15 | — | Oct 19, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- 131K tokens
- Total parameters
- 1.03T
- Active parameters
- 32B
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesmoonshotai/Kimi-K2-Thinking, moonshotai/Kimi-K2-Thinking
Explicit Unknowns
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
moonshotai/Kimi-K2-Thinking developer model repositoryMoonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Thinking README.md at a51ccc050d73Moonshot AI · observed Aug 28, 2026OpenRouter moonshotai/kimi-k2-thinking model APIOpenRouter · observed Aug 28, 2026moonshotai/Kimi-K2-Thinking Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026moonshotai/Kimi-K2-Thinking config.json at a51ccc050d73Moonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Thinking immutable Hub API metadataMoonshot AI · observed Aug 28, 2026Kimi Research Blog release indexMoonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Thinking tokenizer_config.json at a51ccc050d73Moonshot AI · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026Openrouter catalogOpenrouter · observed Oct 19, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Kimi K2 ThinkingMoonshot AI | vs | Kimi K3Moonshot AI | family variantstext |
Kimi K2 ThinkingMoonshot AI | vs | cross-developer peerstext | |
Kimi K2 ThinkingMoonshot AI | vs |  DeepSeek V4 ProDeepSeek | cross-developer peerstext |
Kimi K2 ThinkingMoonshot AI | vs | cross-developer peerstext | |
Kimi K2 ThinkingMoonshot AI | vs | DeepSeek R1DeepSeek | cross-developer peerstext |
Kimi K2 ThinkingMoonshot AI | vs | DeepSeek V3.2DeepSeek | cross-developer peerstext |
Kimi K2 ThinkingMoonshot AI | vs | Kimi K2 InstructMoonshot AI | family variantstext |
Kimi K2 ThinkingMoonshot AI | vs | Kimi K2.5Moonshot AI | family variantstext |
Kimi K2 ThinkingMoonshot AI | vs | Kimi K2.7 CodeMoonshot AI | family variantstext |
Kimi K2 ThinkingMoonshot AI | vs |  GLM 5Z.ai | cross-developer peerstext |
Kimi K2 ThinkingMoonshot AI | vs | GLM 5.1Z.ai | cross-developer peerstext |
Kimi K2 ThinkingMoonshot AI | vs | GLM 5.2Z.ai | cross-developer peerstext |
Questions
Kimi K2 Thinking FAQs
What is Kimi K2 Thinking?+
Kimi-K2-Thinking is an open-weight language model published by Moonshot AI. It is developed by Moonshot AI and its current sourced lifecycle status is active.
What inputs and outputs does Kimi K2 Thinking support?+
Kimi K2 Thinking's current record lists Text as input and Text as output.
How much context does Kimi K2 Thinking support?+
The current record lists a 262K-token context window and a maximum output of 131K tokens.
Is Kimi K2 Thinking available through an API?+
Kimi K2 Thinking is marked as API-available. The directly sourced provider records currently include Hugging Face and Openrouter.
How large is Kimi K2 Thinking?+
The current record lists 1.03T total parameters and 32B active parameters. Its architecture is DeepseekV3ForCausalLM.
What capabilities and tasks does Kimi K2 Thinking support?+
Kimi K2 Thinking's recorded capabilities are chat, generation, reasoning, and tools. Its supported tasks are text.
How much does Kimi K2 Thinking cost through an API?+
The lowest directly sourced prices currently attached to Kimi K2 Thinking are $0.60 per million input tokens through Openrouter and $2.50 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Kimi K2 Thinking be self-hosted?+
Kimi K2 Thinking is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Kimi K2 Thinking have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are moonshotai/Kimi-K2-Thinking.
Which models can Kimi K2 Thinking be compared with?+
The current compatible peer set includes Kimi K3, NVIDIA Nemotron 3 Ultra 550B A55B BF16, DeepSeek V4 Pro, Qwen3.8 2.4T A95B, and DeepSeek R1. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →