Moonshot AI opens Kimi K3.1 Pro through standard and high-speed APIs
Kimi K3.1 Pro launches as the first model in the K3.1 series, with 3-trillion-class scale, native vision and a 1-million-token context window across standard and faster API options.
AT A GLANCE
Key points
- K3.1 Pro is the first 3-trillion-class model in the K3.1 series, with native vision and a 1-million-token context window.
- Standard and Highspeed variants are available; the documentation claims roughly two to three times the speed for Highspeed.
- The API is compatible with OpenAI Responses and Anthropic Messages formats.
What is changing?
Moonshot AI has made Kimi K3.1 Pro, the first model in its K3.1 series, available in standard and Highspeed variants. The company describes it as a new flagship at 3-trillion-class scale, with native visual understanding and a 1-million-token context window.
According to Moonshot’s documentation, the model improves on earlier versions in coding, 3D content creation, financial research and modeling. The `kimi-k3.1-pro` and `kimi-k3.1-pro-highspeed` identifiers can be called through an OpenAI-compatible Responses API and an Anthropic-compatible Messages API. The Highspeed option is said to deliver the same capabilities at roughly two to three times the speed.
Standard pricing is listed at $2 per million input tokens and $10 per million output tokens; Highspeed costs $4 and $20 respectively. Cache hits cost $0.20 per million tokens on both variants. Capability and speed statements are provider claims, and no current independent benchmark is presented.
Explore the original sources
Source date: 23 October 2026.
Published by AI Radar: 23 Oct 2026, 21:06 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…