Identity
- Status
- active
- Developer ID
moonshotai/Kimi-K2-Instruct- Released
- Jul 11, 2025
- Version
- Kimi-K2-Instruct
- License
- other
Moonshot AIKimi K2 Instruct
Kimi-K2-Instruct is an open-weight language model published by Moonshot AI.
- Token context
- 131K tokens
- Inputs
- Text
- Outputs
- Text
- Released
- Jul 11, 2025
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 OpenrouterAvailable | $0.57 | $2.30 | — | — | Aug 29, 2026 | Provider-reported |
Benchmarks
All benchmark results →| Aider Polyglotpolyglot-225-5dc9490bb35f | 59.11 | 1,617.1 | 225 | diff; aider 0.85.3.devtotal | Recomputedwinner eligible | Third-party benchmark |
| Berkeley Function Calling Leaderboardv4-ede5081a24bc | 59.06 | — | — | Moonshotai-Kimi-K2-Instruct (FC)unknown | Recomputedwinner eligible | Third-party benchmark |
At a Glance
Model Facts
Capacity
- Token context
- 131K tokens
- Maximum output
- Unknown
- 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
- No
- Vision
- No
- Tool calling
- Yes
- Capabilities
- chat, generation, 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-Instruct, moonshotai/Kimi-K2-Instruct
Explicit Unknowns
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
moonshotai/Kimi-K2-Instruct developer model repositoryMoonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Instruct README.md at fd1984e2b7a3Moonshot AI · observed Aug 28, 2026OpenRouter moonshotai/kimi-k2 model APIOpenRouter · observed Aug 29, 2026moonshotai/Kimi-K2-Instruct Hugging Face inference-provider mappingHugging Face · observed Aug 28, 2026moonshotai/Kimi-K2-Instruct config.json at fd1984e2b7a3Moonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Instruct immutable Hub API metadataMoonshot AI · observed Aug 28, 2026Kimi Research Blog release indexMoonshot AI · observed Aug 28, 2026moonshotai/Kimi-K2-Instruct tokenizer_config.json at fd1984e2b7a3Moonshot AI · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Kimi K2 InstructMoonshot AI | vs | cross-developer peerstext | |
Kimi K2 InstructMoonshot AI | vs |  DeepSeek V4 Pro BaseDeepSeek | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs | cross-developer peerstext | |
Kimi K2 InstructMoonshot AI | vs | DeepSeek V3DeepSeek | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs |  Llama 3.1 405BMeta | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs | cross-developer peerstext | |
Kimi K2 InstructMoonshot AI | vs |  MiniMax M2.5MiniMax | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs | MiniMax M2.7MiniMax | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs | Kimi K2 ThinkingMoonshot AI | family variantstext |
Kimi K2 InstructMoonshot AI | vs | Kimi K2.6Moonshot AI | family variantstext |
Kimi K2 InstructMoonshot AI | vs |  GLM 5Z.ai | cross-developer peerstext |
Kimi K2 InstructMoonshot AI | vs | GLM 5.1Z.ai | cross-developer peerstext |
Questions
Kimi K2 Instruct FAQs
What is Kimi K2 Instruct?+
Kimi-K2-Instruct 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 Instruct support?+
Kimi K2 Instruct's current record lists Text as input and Text as output.
How much context does Kimi K2 Instruct support?+
The current record lists a 131K-token context window and does not report a maximum output length.
Is Kimi K2 Instruct available through an API?+
Kimi K2 Instruct is marked as API-available. The directly sourced provider records currently include Hugging Face and Openrouter.
How large is Kimi K2 Instruct?+
The current record lists 1.03T total parameters and 32B active parameters. Its architecture is DeepseekV3ForCausalLM.
What capabilities and tasks does Kimi K2 Instruct support?+
Kimi K2 Instruct's recorded capabilities are chat, generation, and tools. Its supported tasks are text.
How much does Kimi K2 Instruct cost through an API?+
The lowest directly sourced prices currently attached to Kimi K2 Instruct are $0.57 per million input tokens through Openrouter and $2.30 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Kimi K2 Instruct be self-hosted?+
Kimi K2 Instruct is an open-weight model. Self-hosting is supported, and the recorded license is other.
Does Kimi K2 Instruct have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are moonshotai/Kimi-K2-Instruct.
Which models can Kimi K2 Instruct be compared with?+
The current compatible peer set includes NVIDIA Nemotron 3 Ultra 550B A55B BF16, DeepSeek V4 Pro Base, Qwen3.8 2.4T A95B, DeepSeek V3, and Llama 3.1 405B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →