MoonshotAI: Kimi K3Active

moonshotai/kimi-k3

Kimi K3 is Kimi’s most capable model to date, with 2.8 trillion parameters. Built on Kimi Delta Attention, a hybrid linear attention mechanism, and Attention Residuals, it offers native visual understanding and a 1M-token context window for frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning.

By:MoonshotAIInput Type:Output Type:Publish time:2026-07-17

Providers

Route requests across multiple providers. Copy a provider slug to set your preference.

ProviderCache Hit RateContext

Moonshot AI

moonshotai

-$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:-/ M tokens1.05M--

NovitaAI

novita

96.0%$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:-/ M tokens1.05M4.89s12.8tps

TencentCloud

tencent-cloud

-$3/ M tokens$15/ M tokensRead:0.3/ M tokensWrite:-/ M tokens1.05M--

Uptime

24hours

Direct request success rate on AI Gateway and per-provider.

Oct 26, 11:24

Moonshot AI100.00%

NovitaAI100.00%

Throughput

24hours

P50 throughput on live AI Gateway traffic, in tokens per second (TPS).

Oct 26, 19:00

NovitaAI12.8 tps

Latency

24hours

P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds.

Oct 26, 19:00

NovitaAI4.89s

Activity

Token volume and request traffic to this model over time.

Token Consumption

Oct 25

Moonshot AI-

NovitaAI54.7M

TencentCloud-

Token volume broken down by the provider that served each request. Larger segments indicate providers handling more of this model's traffic.

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis

Intelligence Index43.6

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. View All

Token Ranking

WorkBuddyWorkBuddy is a desktop AI agent for everyday office work, developed by Tencent Cloud's CodeBuddy team. It uses multi-agent orchestration to break a natural-language goal into sub-tasks and return finished deliverables such as reports, slide decks, spreadsheets and research briefs, and can also be driven from IM platforms like Slack, Telegram, Discord and WeCom. It supports connectors, Skills and MCP, local file operations, and switching between built-in or custom OpenAI-compatible models.

25.3M383.68%

LiteLLMLiteLLM is an open-source AI gateway and Python SDK developed by BerriAI that provides a single, unified OpenAI-compatible interface for calling 100+ LLM providers such as OpenAI, Anthropic, Gemini, Bedrock and Azure. It can be embedded as a library in application code or self-hosted as a proxy server, offering virtual keys, spend tracking, budgets, guardrails, load balancing, fallbacks and an admin dashboard for teams and organizations.

8.8M

OpenCodeOpenCode is an open-source, MIT-licensed AI coding agent built by the team behind SST (now Anomaly), available as a terminal TUI/CLI, a desktop app, and IDE extensions. It is model-agnostic and works with many LLM providers or local models, letting developers explore codebases, plan changes, edit files, run shell commands, and use LSP and MCP integrations directly from their workflow.

7.3M89.98%

OpenQiao Studio ChatOpenQiao Studio Chat is the built-in web chat workspace of the OpenQiao AI model aggregation platform, operated by OpenQiao Singapore. It lets users converse with many different large language models in a browser GUI, with features such as multi-model side-by-side comparison, multimodal file input, Artifacts generation, web search, image generation/editing and voice input/output.

2.5K

CodexOpenAI Codex is a coding agent from OpenAI that runs locally on a developer's machine, available as a terminal CLI (codex / codex exec), a macOS and Windows desktop app, and IDE extensions. It can explore repositories, edit files, run commands and tests, review diffs, and automate longer-running software engineering tasks.

Related Models

More models from MoonshotAI

MoonshotAI: Kimi K3.1 Pro Highspeed

24.85Mtokens

Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, delivering comparable intelligence with approximately 2–3× higher output speed and up to a 1M-token context window. It is optimized for long-horizon reasoning and agentic workflows, with strong performance in coding, 3D creation, financial analysis, tool use, and multimodal understanding of text, images, and video.

MoonshotAI: Kimi K3.1 Pro

43.11Btokens

Kimi K3.1 Pro is MoonshotAI’s flagship reasoning model with a 1M-token context window, built for long-horizon agent workflows and multimodal understanding with image and video input. It delivers strong performance in coding, 3D creation, and financial research, while supporting streaming output, structured generation, and tool calling with configurable reasoning effort.

MoonshotAI: Kimi K2.8 Preview

890.36Mtokens

Kimi K2.8 Preview delivers overall performance close to K3 with more efficient thinking. It supports adjustable thinking effort levels aligned with K3’s reasoning tiers, and provides up to 1M-token ultra-long context.