Kimi-K2 logo

Kimi-K2

MoonshotAI/Kimi-K2

Large language model series developed by Moonshot AI team

GraphCanon updated 2w · GitHub synced 2w

11k stars902 forksLast push 7mo Other

Decision brief

Kimi K2, developed by Moonshot AI team, brings a large language model series providing an API compatible with OpenAI and Anthropic interfaces.

Good fit when

  • - When looking to deploy models on specific inference engines like vLLM or SGLang which are well-supported for Kimi K2.
  • - If you require the unique temperature mapping feature of `real_temperature = request_temperature * 0.6` specifically to maintain compatibility with Anthropic applications without extensive code re-w

Avoid when

  • - Avoid using it if your application strictly requires a different model format that isn't supported by Kimi K2 (currently block-fp8).
  • - Do not use this tool if you are dependent on running inference outside of the recommended engines, as compatibility and performance may be compromised without specific support.
Pricing:
unknown - N/A
Requirements:
Model deployment examples are available for vLLM and SGLang, aiding in setup and integration.

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (197d since push)
As of 2w
Provenance
Not a fork · Organization account
As of 2w
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/MoonshotAI/Kimi-K2

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Kimi K2 is a series of large language models created by the Moonshot AI team, offering an API compatible with OpenAI and Anthropic interfaces.

Capability facts

No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).

Categories

Tags

README

4. Deployment

[!Note] You can access Kimi K2's API on https://platform.moonshot.ai , we provide an OpenAI/Anthropic-compatible API for you.

The Anthropic-compatible API maps temperature by real_temperature = request_temperature * 0.6 for better compatiblity with existing applications.

Our model checkpoints are stored in block-fp8 format, you can find it on Huggingface.

Currently, it is recommended to run Kimi-K2 on the following inference engines:

  • vLLM
  • SGLang
  • KTransformers
  • TensorRT-LLM

Deployment examples for vLLM and SGLang can be found in the Model Deployment Guide.



6. License

Both the code and the model weights are released under the Modified MIT License.


For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.