Kimi

Kimi

Freemium

Moonshot AI's open-weight LLM family: long context, agentic coding, and bilingual performance.

LLM
Open-weight

Published 29 May 2026Last updated 3 November 2026

Scores

Popularity3/5

Established

Very popular in China with a large consumer user base on kimi.ai. Growing international profile — K2 repo reached 10.7k GitHub stars rapidly, and the Kimi K2 family is among the most downloaded on Hugging Face. Still behind Llama and GPT-series internationally.

Learning Curve2/5

Easy

The Moonshot AI API is fully OpenAI-compatible — developers already familiar with the OpenAI SDK can switch by changing the base URL and API key. Open-weight models follow standard Hugging Face download patterns. The main friction is English documentation lagging behind Chinese-language resources.

Flexibility4/5

Flexible

Open-weight releases (K2, K2.5, K2.6, Kimi-VL) allow full self-hosting and customization. The managed API covers chat, vision, and tool use. No fine-tuning on the managed API limits flexibility there, but the open weights compensate. Multiple access paths (API, chat, CLI, Hugging Face).

Performance5/5

Best-in-class

Kimi K2 and K2.6 are top-tier on SWE-bench Verified and agentic coding benchmarks — competitive with GPT-4o and Claude Sonnet. K1.5 matched o1 on math at launch. 256K context is a standout for long-document tasks.

Portability4/5

Portable

Open-weight models are fully portable — download from Hugging Face, run on any compatible GPU infrastructure. The API uses OpenAI-compatible schema, reducing switching costs. Larger models (1T parameters) require significant hardware to self-host at full capacity.

About Kimi

Kimi is the model family and AI assistant from Moonshot AI, a Beijing-based lab. Its models are known for very long context windows, strong agentic coding, and bilingual Chinese and English performance, and Moonshot publishes the weights of its major releases on Hugging Face as well as selling API access and consumer subscriptions.

The flagship is Kimi K3.1 Pro, the first model of the K3.1 series: a 3-trillion-parameter-class model built for long-horizon coding and end-to-end knowledge work, with a one-million-token context window, vision input, and selectable reasoning effort, plus a Highspeed variant that runs two to three times faster. The previous-generation K3 stays available. The older K2 line, including the K2.7-Code coding specialist, is closed to new users and being retired.

The weights are open but not all under the same terms. The K2 checkpoints use a modified MIT licence, while K3's licence adds conditions for the largest users: companies that sell model access as a service and earn more than twenty million dollars a year must sign a separate agreement with Moonshot, and very large consumer products must display "Kimi K3". Internal use is exempt.

Developers reach the models through the OpenAI-compatible API at platform.kimi.ai, priced per million tokens with automatic context caching, a Batch API at 60% of the standard price, and cloud platforms such as Amazon Bedrock. Kimi Code is Moonshot's terminal coding agent. The kimi.com assistant has a free tier and paid memberships, which Moonshot has restructured several times; Kimi Code is included only on the higher paid tiers.

Key Features

  • Kimi K3.1 Pro flagship: 1M-token context, vision input, selectable reasoning effort
  • K3.1 Pro Highspeed variant at two to three times the speed
  • Previous-generation K3 still available on the API
  • Open weights on Hugging Face (modified MIT; K3 adds large-operator terms)
  • OpenAI-compatible API at platform.kimi.ai
  • Automatic context caching and a Batch API at 60% of standard price
  • Kimi Code terminal agent for agentic coding
  • Available on Amazon Bedrock as well as Moonshot's own API

Pros

  • Frontier-level open-weight models for agentic coding
  • Downloadable weights for self-hosting and research
  • OpenAI-compatible API makes switching from OpenAI simple
  • Very long context for large codebases and documents
  • Strong bilingual Chinese and English performance
  • Context caching lowers the cost of repeated prompts

Cons

  • K3's licence requires a deal with Moonshot for large Model-as-a-Service operators
  • Self-hosting the largest models needs a multi-GPU cluster
  • English documentation lags the Chinese-language resources
  • Consumer membership tiers have changed repeatedly, which makes plans hard to compare
  • Fast generation turnover: the whole K2 line is being retired within months of K3's release
  • No fine-tuning through the public API

Kimi Pricing

Freemium
Open weightsFree
  • K2 checkpoints under a modified MIT licence
  • K3 weights free except for large Model-as-a-Service operators
  • Self-hosted from Hugging Face
kimi.com FreeFree
  • Free tier of the Kimi assistant
  • Limited agent and chat usage
kimi.com MembershipContact sales
  • Four paid membership tiers, monthly or annual
  • More agent usage and longer conversations on higher tiers
  • Kimi Code on the higher tiers, with a weekly usage cap
API: Kimi K3Contact sales
  • $3.00 per 1M input tokens ($0.30 on cache hit)
  • $15.00 per 1M output tokens
  • Previous generation; 1M-token context, vision input
API: Kimi K2.6Contact sales
  • $0.95 per 1M input tokens ($0.16 on cache hit), $4.00 per 1M output
  • Closed to new users; retiring by the end of December 2026
API: Kimi K2.7-CodeContact sales
  • $0.95 per 1M input tokens ($0.19 on cache hit), $4.00 per 1M output
  • Closed to new users; retiring by the end of December 2026
API: Kimi K3.1 ProContact sales
  • $2.00 per 1M input tokens ($0.20 on cache hit)
  • $10.00 per 1M output tokens
  • 1M-token context, vision input, reasoning effort low/high/max

Tech Stacks with Kimi

OpenCode Dev Stack

Developer

OpenCode as the coding agent, in the terminal, the desktop app, an IDE extension, or the browser, running open-weight models such as DeepSeek, GLM, and Kimi, with your pick of GitHub or GitLab for version control.

LLM:
Version Control:
Server add-on:
Remote Access add-on:
Session Persistence add-on:
Terminal add-on:
Code Review add-on:
Model Inference add-on:
Model Aggregator add-on:
CI/CD add-on:
Containerization add-on:

Orca Dev Stack

Developer

Orca runs several coding agents side by side, each in its own git worktree, with your pick of agents and models underneath and GitHub or GitLab for version control.

Coding Agent:
LLM:
Version Control:
Server add-on:
Remote Access add-on:
Code Review add-on:
CI/CD add-on:

Herdr Dev Stack

Developer

Herdr keeps several coding agents running in persistent terminal sessions on your laptop or a server, with your pick of agents and models and GitHub or GitLab for version control.

Coding Agent:
LLM:
Version Control:
Server add-on:
Remote Access add-on:
Terminal add-on:
Code Review add-on:
CI/CD add-on:

Tools Related to Kimi

Alternatives to Kimi(8)

Kimi is Moonshot AI's long-context family with strong agentic coding and Chinese and English performance; Mistral is Europe's open-weight family, available via its API, major clouds, or self-hosting. Mistral suits EU data needs, Kimi long-context coding.

Both are Chinese open-weight families built for long context and agentic coding: Kimi is known for bilingual Chinese and English performance, MiniMax M3 adds native multimodal input with a 1M-token context. Compare them on your own coding benchmarks.

Kimi and Qwen are open-weight LLM alternatives from Chinese AI labs. Kimi differentiates with extremely long context (up to 1M tokens); Qwen offers a wider range of model sizes and better multilingual coverage.

Kimi and GLM are Chinese open-weight LLM alternatives from Moonshot AI and Zhipu AI (Z.ai) respectively. Both are bilingual; Kimi differentiates with long context (up to 1M tokens) and strong reasoning via K1.5/K2.

Kimi and Meta Llama are open-weight LLM alternatives. Kimi differentiates with very long context windows and strong reasoning; Llama has a much larger global ecosystem and fine-tune community.

Kimi and Google Gemma are open-weight LLM alternatives. Kimi leads on context length and reasoning; Gemma leads on small-model efficiency suitable for edge and on-device deployment.

Vendor

Moonshot AI

Moonshot AI

Website

Tags

Open SourceWeb

Details

Maintained
Yes