Released 34 days after Kimi K2.7 Code · All Moonshot releases
Kimi K3, released July 16, 2026, is Moonshot's largest model to date and a substantial step up in scale from the 1 trillion parameter Kimi K2 line. It uses a Mixture-of-Experts architecture with 2.8 trillion total parameters and 104 billion active per token, selecting 16 of 896 experts across 93 layers. The model targets long-horizon coding, knowledge work, and reasoning, scoring 93.5 on GPQA Diamond, 91.2 on BrowseComp, 88.3 on Terminal-Bench 2.1, and 67.5 on DeepSWE. Its 1,048,576 token context window is built for whole-repository work and extended agent runs, where the reasoning trace itself grows large. Vision is native, handled by the 401 million parameter MoonViT-V2 encoder, with 81.6 on MMMU-Pro. K3 runs in preserved thinking history mode, so multi-turn calls should pass complete assistant messages back including their reasoning content rather than stripping it. It is quantization-aware trained from the SFT stage onward using MXFP4 weights with MXFP8 activations, and its weights are published under the Kimi K3 License.
Kimi K3 runs on 14 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| EU | No | $3.47 | $17.33 | ||
| US | No | $2.85 | $14.25 | ||
| US | No | $2.85 | $14.25 | ||
| Multi | No | $3.00 | $15.00 | ||
| Multi | No (opt-in) | $3.00 | $15.00 | ||
| Multi | Yes | $3.00 | $15.00 | ||
| US | No | $2.50 | $14.00 | ||
| US | No | $6.00 | $22.50 | ||
| Multi | No | $3.00 | $15.00 | ||
| US | No | $3.00 | $15.00 | ||
| US | No | $3.00 | $15.00 | ||
| EU | No | $3.00 | $15.00 | ||
| EU | No | $3.00 | $15.00 | ||
| US | No | $3.00 | $12.75 |
Kimi K3 runs on 7 independently monitored routes through the Opper gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 6 further routes for this model are not on the board yet and are not counted above. See uptime for every provider Opper monitors.
Each route hosting Kimi K3 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; unknown; DPA available.
Zero data retention is not on by default — a moderation hold applies. No training on customer data. US; dpf sccs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training by default; opt-in possible. GLOBAL; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring. Trained on customer data by default. GLOBAL; unknown.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring, 30-day retention. No training on customer data. US; SCCs; DPA available.
Zero data retention is not on by default — abuse monitoring. No training on customer data. GLOBAL; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EEA; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call Kimi K3 through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "berget/kimi-k3",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
