The update introduces new Zero Data Retention hosting options for both Kimi K3.1 Pro and Kimi K3.1 Pro Highspeed, which were previously limited strictly to Moonshot AI. Both model variants support a 1-million-token context window alongside image input capabilities, bringing enhanced financial analysis, 3D modeling, and coding performance. Developers can route queries across various standard APIs or through tools like Cursor and Codex using the Vercel CLI. AI Gateway charges no extra platform fees or markups on inference, including instances where users bring their own keys.
Key points
Setting Zero Data Retention rules guarantees traffic never falls back to unprotected endp…: Setting Zero Data Retention rules guarantees traffic never falls back to unprotected endpoints if compliant providers are unavailable.
Development teams can integrate these models directly into coding agents like Cursor, Cod…: Development teams can integrate these models directly into coding agents like Cursor, Codex, and Claude Code via the Vercel CLI.
The Kimi K3.1 Pro base model delivers targeted performance upgrades in 3D modeling, codin…: The Kimi K3.1 Pro base model delivers targeted performance upgrades in 3D modeling, coding tasks, and financial analysis.
Sources checked by our analysis pipeline: 1
Kimi K3.1 Pro and its higher-speed version, Kimi K3.1 Pro Highspeed, are now available on AI Gateway from more Zero Data Retention (ZDR) providers. Until today, Moonshot AI was the only provider serving either model.
K3.1 Pro improves on earlier Kimi models in coding, 3D modeling, and financial analysis, and can carry long agent runs from a small fix to a full project. Both models have a 1M-token context window and accept image input, and Highspeed suits interactive work like coding agents, where response time matters.
Call either model through the AI SDK, the Chat Completions, Responses, and Anthropic Messages APIs, or a coding agent connected to AI Gateway. For Highspeed, use moonshotai/kimi-k3.1-pro-highspeed
in place of the model name below.
Use moonshotai/kimi-k3.1-pro
as the model name:
import { streamText } from 'ai';
const result = streamText({ model: 'moonshotai/kimi-k3.1-pro', prompt: 'Write a Python function that redacts email addresses from a log line.', providerOptions: { gateway: { zeroDataRetention: true, }, },});
Setting zeroDataRetention
in the gateway provider options requires ZDR for that request. To require it for every request your team sends,…
Enterprises, startups, and public sector organizations are shifting toward freely accessible models to secure reduced overhead, operational autonomy, and infrastructure control. However, the rapid advancement of rival Chinese architectures is intensifying competitive pressure on American developers trying to monetize open source frameworks. Hugging Face leadership warns that navigating infrastructure choices and tool selection remains crucial for firms trying to build sustainable businesses.
Educational institutions are clashing with Big Tech over how aggressively automated tools should be integrated into academic environments. Although Google maintains a massive classroom footprint, administrators are pushing back against rigid configurations that force artificial intelligence into everyday student research. This growing dissatisfaction has opened a strategic window for privacy-focused rivals to challenge long-standing school software monopolies.
Wall Street's post-election gains revealed a growing rift in the artificial intelligence sector following Democratic congressional victories and the passage of nationwide data center restrictions. While incumbent tech leaders benefit from forced capital spending discipline, emerging cloud competitors and equipment suppliers face steep challenges over future facility buildouts. Investors expect existing digital infrastructure monopolies to tighten their market dominance under the new regulatory climate.