GraphCanon updated 2w · GitHub synced 2w
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-K2Similar 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 * 0.6for 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.