Skip to main content
πŸ“– The AI Tool Bible

AI tools linked to Kimi K3

Kimi K3 is a model from Moonshot. 18 tools in this directory are linked to it.

Each tool is listed because text on its own profile, or on its own website or documentation (quoted on its card with the page it comes from), names Kimi K3 by its exact name. That is a keyword match, not a test: a tool that names several models may not run this one in every plan or version, so read the quoted text and check the tool before relying on it.

Tools linked to Kimi K3

  • BraintrustEvaluation

    Braintrust is an AI observability platform for tracing production, running evals, and catching regressions before they reach users.

    Its site says: β€œKimi K3 and DeepSeek V4 Flash 0731” source page

  • Together AIFine-tuning

    Fine-tune & serve open-weight models (Llama, Mistral, DeepSeek).

    Its site says: β€œ| Kimi K3 (US-only) | $3.75 | $0.375 | $18.75” source page

  • WarpCoding

    The agentic development environment, from the terminal up

    Its site says: β€œAccess Fable 5, Claude Opus 5, GPT-5.6, Gemini 3.1 Pro, GLM 5.2, Kimi K3, and more.” source page

  • ClineCoding

    Open-source agentic coding assistant that plans, edits, and runs code inside your IDE

    Its site says: β€œView model Moonshot AI Kimi K3” source page

  • LM StudioAgents

    LM Studio Bionic is a natively local agent for open models built for creativity, work, and code.

    Its site says: β€œKimi K3 is Moonshot AI’s 2.8T-parameter flagship model for long-horizon agentic work, with native vision, always-on reasoning, and a 1M-token context window.” source page

  • Cloud browser infrastructure and hosted agents for AI automation, with stealth browsers available at $0.02 per hour.

    Its site says: β€œKimi K3 (Moonshot) is now available in Browser Harness.” source page

  • SimAgents

    Open-source AI workspace for building, deploying, and managing AI agents.

    Its site says: β€œkimi-k3 Β· Input $3 /1M Β· Output $15 /1M Β· 1.05M context” source page

  • UnslothFine-tuning

    Open-source LLM fine-tuning toolkit with custom kernels that train 2-30x faster and use up to 90% less VRAM.

    Its site says: β€œ[GLM-5.3-Flash](https://unsloth.ai/docs/models/glm-5.3-flash), [Kimi K3](https://unsloth.ai/docs/models/kimi-k3), [Qwen-Image-2.1](https://unsloth.ai/docs/models/qwen-image-2.1), MiniMax-H3, [DeepSeek-V4](https://unsloth.ai/docs/models/deepseek-v4), [Gemma” source page

  • Notion AIWriting

    In-line AI inside your Notion docs and databases.

    Its site says: β€œYou get access to all the latest frontier models in Notion, including Opus 5, GPT-5.6 Sol, and Kimi K3.” source page

  • OllamaCoding

    The de facto runtime for running open-weights LLMs locally, now with a paid cloud tier for bigger models.

    Its site says: β€œKimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.” source page

  • Conversational answer engine that cites its sources by default.

    Its site says: β€œKimi K3 β€” Moonshot AI’s flagship reasoning model.” source page

  • TaskadeAgents

    Taskade turns one prompt into apps, AI agents, and automated workflows in one living workspace.

    Its site says: β€œ| Kimi K3 Available Released Jul 2026 1.05M context | Available | Jul 2026 | 1.05M | No app From 1 build” source page

  • ManifestAgents

    Open-source LLM router that fans your agent traffic across providers and your existing AI subscriptions.

    Its site says: β€œd3d44e3: Add Kimi K3 ( cline-pass/kimi-k3 ) to the ClinePass subscription’s known models list.” source page

  • AI API gateway for Claude Code, Codex, and coding agents.

    Its site says: β€œ| kimi-k3.1-pro , kimi-k3 , qwen3.8-max , qwen3.8-flash , qwen3.7-max , qwen3.7-flash , MiniMax-M3 , minimax-m3.1-flash , doubao-seed-2.1-pro , doubao-seed-2.1-lite ,” source page

  • Yomu AIWriting

    Academic writing assistant for essays, papers, and theses.

    Its site says: β€œFrontier models: GPT-6.1 Sol, Claude 5.5 Sonnet & Opus, Grok 4.7, DeepSeek V4, Kimi K3 & more” source page

  • AirLLMFine-tuning

    AirLLM 2.8T LLM inference with single 4GB GPU

    Its site says: β€œ[2026/07] **Kimi K3 (2.8T)** support: the largest open-source model runs on a single card in **3.72GB** of VRAM, measured end to end on one RTX 6000 Ada.” source page

  • CowAgentAgents

    Open-source AI assistant and agent harness that plans tasks, runs tools and skills, and grows with long-term memory and knowledge.

    Its site says: β€œ| Kimi | kimi-k3.1-pro / kimi-k3 | βœ… | βœ… | | | |” source page

  • Open-source, model-agnostic terminal coding agent

    Its site says: β€œ| Moonshot AI (API) | /provider or env vars | Direct Moonshot API, including Kimi K3.” source page

Sourced facts about Kimi K3

Context window
1.0M tokens
Weights
Proprietary (weights not released)

Source: AI Model Watch, checked 2026-11-16.

All models Β· Browse every AI tool