Kimi K3: Complete Guide to Moonshot's 2.8T Model (2026)

Kimi K3 is the newest flagship AI model from Moonshot AI, officially launched on July 16, 2026. It is the largest open-weight model ever released — a 2.8-trillion-parameter mixture-of-experts system with a 1-million-token context window, native image and video understanding, and benchmark scores that put it within striking distance of GPT-5.6 Sol and Claude Fable 5 at roughly half the cost per task.

This is the hub guide. Each section below gives you the essentials, then links to a dedicated deep-dive if you want more detail on that topic.

Many people search for it as “Kimi 3.0” — the official name is Kimi K3, following Kimi K2 from 2025.

What is Kimi K3?

Kimi K3 is a frontier-class large language model built by Moonshot AI, the Beijing-based lab behind the Kimi assistant. Where Kimi K2 was a strong open-weight model with a 1T-parameter architecture, K3 is a generational leap: nearly 3× the parameters, 4× the context window, and two brand-new architectural techniques — Kimi Delta Attention (KDA) and Attention Residuals — that make it dramatically faster on long contexts.

Three things define K3:

1. Scale with efficiency. 2.8 trillion total parameters, but only 16 of its 896 experts are active per token. You get frontier intelligence without frontier-level inference cost.
2. A 1M-token context window. K3 can hold entire codebases, books, or hours of video transcripts in a single prompt — and its KDA architecture makes long-context decoding up to 6.3× faster than K2.
3. Agentic strength. K3 is built for multi-step, tool-using work: coding agents, browser automation, spreadsheets, and deep research. It ranks #1 on 4 of 8 real-world agentic benchmarks in Moonshot’s launch suite.

Independent testers at Artificial Analysis place K3 at #4 out of 189 AI models (score 57), ahead of Claude Opus 4.8 and GPT-5.5 — the highest rank ever achieved by an open-weight model.

Key specifications at a glance

Spec	Kimi K3
Total parameters	2.8T
Architecture	KDA + Attention Residuals + Stable LatentMoE
Experts	896 (16 active per token)
Context window	1,048,576 tokens (1M)
Vision / video input	Native
Long-context decode	Up to 6.3× faster than K2
Scaling efficiency	~2.5× better than K2
Weights license	Modified MIT (releases July 27)

For the full breakdown of every spec — including what KDA and Attention Residuals actually do, and why the expert count matters — read the dedicated guide: Kimi K3 Specifications Explained.

Benchmark performance

K3’s launch benchmarks show it beating or matching the best closed models on real-world agentic tasks:

Benchmark	Kimi K3	Best competitor	Result
Program Bench	77.8	GPT-5.6 Sol (77.6)	K3 #1
SWE Marathon	42.0	Claude Opus 4.8 (40.0)	K3 #1
BrowseComp	91.2	GPT-5.6 Sol (90.4)	K3 #1
SpreadsheetBench 2	34.8	Claude Fable 5 (34.7)	K3 #1
Automation Bench	30.8	GPT-5.6 Sol (29.7)	K3 #1
Terminal-Bench 2.1	88.3	GPT-5.6 Sol (88.8)	K3 #2 by 0.5

K3 is also #1 on the Frontend Code Arena leaderboard (K2.6 was #18). Moonshot itself is transparent that K3 still trails GPT-5.6 Sol and Claude Fable 5 overall — but it is the only open model anywhere near them, and it costs far less per completed task.

For the full head-to-head — every benchmark, cost per task, and which model wins for which workload — read Kimi K3 vs GPT-5.6 vs Claude Fable 5 vs Opus 4.8.

Pricing: how much does Kimi K3 cost?

K3’s API pricing is aggressive — Sonnet-tier prices for near-frontier intelligence:

Kimi K3 API	Per 1M tokens
Cache-hit input	$0.30
Cache-miss input	$3.00
Output	$15.00
Avg. cost per benchmark task	$0.94

Thanks to Moonshot’s Mooncake disaggregated inference (with >90% cache-hit rates in coding workloads), K3 works out to roughly 50% cheaper per completed task than Claude Opus 4.8 or GPT-5.5, and about 3× cheaper than Claude Fable 5 ($2.75/task).

If you just want to use K3 rather than build on it, it’s free in the Kimi app — no credit card required. Heavy launch traffic means free tiers can queue; membership skips the line.

How to access Kimi K3

There are four official ways to use K3 today:

1. Kimi app & kimi.com — free chat on iOS, Android, HarmonyOS, or the web. The fastest way to try it.
2. Kimi Work — the desktop app (Windows / Apple silicon, v3.1.0+) for deep research, widgets and dashboards. This is the answer if you’re looking to download Kimi K3 for PC.
3. Kimi Code — terminal + IDE agent. Run it and switch to K3 with the /model command.
4. Kimi API — an OpenAI-compatible endpoint at platform.moonshot.ai. Create an API key, select kimi-k3, and you’re running.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_MOONSHOT_API_KEY",
    base_url="https://api.moonshot.ai/v1",
)

resp = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Refactor this repo"}],
    reasoning_effort="max",  # low / high / max all supported
)

New — two K3 model IDs: the API now lists k3 (up to 1M context; Allegretto members and above) and k3-256k (256K context). Within 256K, k3-256k delivers the same results while consuming about half the quota — ideal for everyday Q&A, code completion, routine feature development, and single-file edits (video input is not supported on it). Both are available to Moderato members and above, and both support low / high / max thinking effort.

One warning: because of the launch hype, clone and phishing sites have appeared imitating Kimi. Before entering any credentials, read Kimi AI Official Website: How to Find the Real One.

Kimi K3 vs Kimi K2

If you used K2, here’s the short version: K3 is not an update — it’s a new generation.

Spec	Kimi K2	Kimi K3
Total parameters	1.0T	2.8T
Architecture	MLA MoE	KDA + AttnRes + Stable LatentMoE
Experts	384	896 (16 active / token)
Context window	256K tokens	1,048,576 tokens
Vision / video input	—	Native
Frontend Code Arena	#18 (K2.6)	#1

The full analysis — including which model still makes sense for self-hosters and fine-tuners — is in Kimi K3 vs Kimi K2: Full Comparison.

Release timeline

• July 16, 2026 — Kimi K3 announced and live in the Kimi app, API, Kimi Work and Kimi Code.
• July 27, 2026 — open weights scheduled for release under a Modified MIT license.

For the story of how the launch unfolded (and how the pre-launch rumors held up), see Kimi K3 Release Date & Rumor Recap.

Limitations to know about

No model is magic, and K3 has real trade-offs:

• Not #1 overall. On independent aggregate testing it sits behind GPT-5.6 Sol and Claude Fable 5. If you need the absolute top score regardless of cost, those still win.
• Self-hosting is heavy. 2.8T parameters means the open weights will demand serious multi-GPU infrastructure. Most people should use the API or app.
• Free-tier queues. Launch traffic means the free tier in the Kimi app can be slow at peak times.
• Reasoning effort defaults to max in the API — great for quality, but drop to low/high (or switch to the k3-256k variant at ~half quota) for simple tasks.

FAQ

Is Kimi K3 free? Yes — you can chat with K3 free in the Kimi app and on kimi.com. The API is paid, and membership plans skip free-tier queues.

Is Kimi K3 open source? The weights release on July 27, 2026 under a Modified MIT license — open-weight, with some usage conditions. Check the license before commercial deployment.

What’s the difference between “Kimi K3” and “Kimi 3.0”? Nothing — they’re the same model. “Kimi K3” is the official name; “Kimi 3.0” is just how many people search for it.

Is Kimi K3 better than GPT-5? On several real-world agentic benchmarks (Program Bench, SWE Marathon, BrowseComp, SpreadsheetBench 2, Automation Bench), yes — K3 scores #1. On overall aggregate intelligence rankings, GPT-5.6 Sol and Claude Fable 5 still lead, but K3 costs roughly half as much per task.

The bottom line

Kimi K3 is the most capable open-weight model ever released, and the first one that genuinely pressures the closed frontier on real-world agentic work — at half the price. Whether you’re a developer looking at the API, a researcher waiting for the July 27 weights, or a curious user who just wants to try it in the app, the guides linked above will take you deeper on every topic.