Kimi K2.7 Code HighSpeed

Kimi K2.7 Code HighSpeed is a coding-focused model from Moonshot AI, designed for long-horizon repository work with less overthinking. It is part of the kimi-k2 line, succeeding Kimi K2.6. It has a 262144-token context window and a 262144-token maximum output. Weights are open. It supports reasoning mode, tool calling, and accepts image, text, and video inputs, returning text. Pricing starts at $0.275 per million input tokens and $1.10 per million output tokens, with cached input at $0.05 per million tokens.

Same headline figures as Kimi K2.6.

Range across the hosts that serve it: up to $1.90 per 1M input tokens.

• ·Long-horizon repository coding
• ·Reduced overthinking in responses
• ·262k token context and output
• ·Open weights and tool calling
• ·Multi-modal input: image, text, video

• Reach for it for long-horizon repository refactoring
• Reach for it for coding tasks needing large context
• Reach for it for multi-modal input coding assistance
• Reach for it for self-hosted coding models

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

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 size?

262144 tokens for both input and output.

Is the model open weights?

Yes, weights are open.

What input types does it accept?

Image, text, and video.