Kimi K3

Kimi K3 is a multimodal model from Moonshot AI for long-horizon agent work. It is the first version of the kimi-k3 line, offering a 1M context and toggleable max-effort thinking. It has a context window of 1,048,576 tokens and a max output of 1,048,576 tokens. Weights are open. It supports reasoning mode and tool calling. It accepts image, text, and video inputs and returns text. Pricing starts at $0.83 per million input tokens and $8.00 per million output tokens, with cached input at $0.195 per million tokens.

First version of its line in the registry.

Range across the hosts that serve it: up to $6.00 per 1M input tokens.

• ·1M token context window for long documents
• ·Max output of 1M tokens
• ·Toggleable max-effort thinking for deep reasoning
• ·Accepts image, text, and video inputs
• ·Open weights served by 68 hosts

• Reach for it for long-horizon agent tasks requiring extensive context
• Reach for it for multimodal analysis combining images, text, and video
• Reach for it for tasks needing large generated outputs up to 1M tokens
• Reach for it for reasoning-heavy workflows with tool calling

68 hosts serve this model at the price above · the maker's documentation

• 8Ember-12026-09-28
• 9Google TPU Runs Kimi 57% Faster Than Nvidia GPU, Using DeepSeek Inference Framework2026-09-27
• 8OpenRouter Analyzes Kimi K3: Open Weights, License Terms, and How to Call It2026-09-24
• 8Artificial Analysis 评测 Step 5 Preview： Intelligence Index 得 44 分，成本约为同级模型 1/2.82026-09-22

4 signals of the archive mention this model, each scored against the published bar. This list is rebuilt from the archive at every build, so it cannot go stale.

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window and max output?

Both the context window and max output are 1,048,576 tokens, so the model can take in and produce up to 1M tokens per request.

Does Kimi K3 support tool calling and reasoning?

Yes, it supports both reasoning mode and tool calling. It also accepts image, text, and video inputs, and returns text.

What is the pricing for Kimi K3?

Input starts at $0.83 per million tokens, output at $8.00 per million tokens, and cached input at $0.195 per million tokens.