Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
At a glance
- Context window
- 1Mtokens
- Max output
- 944Ktokens
- Knowledge to
- —
- Released
- 2026
Capabilities
Benchmarks
- Intelligence index
- 44
- Coding index
- 76
- Agentic index
- 51
Design Arena
| Category | Elo | Win rate |
|---|---|---|
| models · 3d | 1,425 | 69 |
| models · gamedev | 1,404 | 63.1 |
| models · codecategories | 1,388 | 64.7 |
| models · uicomponent | 1,369 | 63 |
| models · dataviz | 1,365 | 64.1 |
| models · website | 1,352 | 60.8 |
| models · svg | 1,335 | 63 |
Standard evaluations
| Benchmark | Score | Tasks |
|---|---|---|
| gpqa_diamond | 0.91 | 1,182 |
| tau_bench_verified_airline | 0.71 | 250 |
Source: Artificial Analysis, Design Arena · as of Sep 16, 2026
Performance
Uptime on IranRouter
18.7%
Reference uptime
100%
Median latency
2,195 ms
Throughput
33.9 tok/s
IranRouter uptime comes from our own automated probes; the reference figures are daily measurements of this model's upstream routes. Each card shows a 30-day average, and a day without data stays empty.
Popularity
- Current rank
- #19
- Rank change, 7 days
- -5
Daily tokens · 90 days
205.7B
Ranked by daily token volume across the global model market; the figure above the chart is the daily average.
Supported parameters
Parameters this model accepts; anything else is ignored.
Quick start
from openai import OpenAI
client = OpenAI(
api_key="ir-...",
base_url="https://iranrouter.com/v1",
)
resp = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[{"role": "user", "content": "سلام!"}],
)
print(resp.choices[0].message.content)Only base_url and the key change; the rest of your code stays as it is.