Kimi K3 API
New512K context · Released Aug 26, 2026 · By Moonshot AI · Modified MIT
Kimi K3 costs $1.85 per million input tokens and $9.00 per million output tokens, against an official rate of $3.00 and $15.00 — 40% below official pricing. It is a Moonshot AI model under the Modified MIT licence, with a 512K context window, callable through an OpenAI-compatible endpoint with the model id moonshotai/kimi-k3. On an agent or chat workload that resends a fixed prompt prefix, where that prefix is billed at the cached rate of $0.37 per million, the saving reaches 65%.
Input
$1.85/M
$3.00/M
Output
$9.00/M
$15.00/M
Savings
40%
off official
- No markup
- OpenAI SDK compatible
- No minimum spend
- Modified MIT
The current open-weight frontier. Half-million-token context and frontier-class reasoning, at roughly a fifth of what closed models charge for the same work.
Copy this and go
The model id is already filled in. Nothing in this snippet needs editing except your key.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://router.xark.io/api/v1" # ← the only line that changes
)
response = client.chat.completions.create(
model="moonshotai/kimi-k3",
messages=[{"role": "user", "content": "Hello"}]
)
Kimi K3 pricing across providers
Rates as published by each provider. We update these when they change; if you spot one that's stale, tell us and we'll fix it.
| Provider | Input | Output |
|---|---|---|
| AI Token Router | $1.85/M | $9.00/M |
| Official (Moonshot AI) | $3.00/M | $15.00/M |
| OpenRouter | $2.94/M | $14.70/M |
| DeepInfra | $2.40/M | $11.50/M |
| Together AI | Not offered | — |
Cached input on Kimi K3 is billed at $0.37/M — roughly 80% below the standard input rate. For agent loops with a large fixed system prompt this is usually the number that matters most.
What it's good at
- Whole-codebase reasoning without a retrieval layer
- Research synthesis over hundreds of documents
- Complex multi-step planning agents
Other text models
Kimi K3 questions
Every figure below is read from the same catalogue entry as the table above, so the two cannot disagree.
What does Kimi K3 cost on AI Token Router, and what is the official rate?
Input is $1.85/M here against $3.00/M official, and output is $9.00/M against $15.00/M official — $1.15/M off every million input tokens and $6.00/M off every million output tokens. The headline 40% blends the two, weighted three to one towards output, because real workloads write far more than they read and a flat average of the two percentages would overstate what you actually save. Both figures are printed side by side on this page: the official rate is the only benchmark that makes ours mean anything.
Can I call Kimi K3 right now?
Yes. A request naming moonshotai/kimi-k3 reaches a live upstream today and is billed at the rates above. 7 of the 24 models in this catalogue are callable right now; the rest are listed at their intended price and marked unavailable on their own pages, so you find that out here rather than from an error at call time.
Does Kimi K3 support prompt caching, and what does a cached token cost?
Yes. A repeated prefix — a fixed system prompt, a tool schema, a document you keep querying — is served from the model's KV cache and billed at $0.37/M instead of the standard $1.85/M, which is 80% below the input rate. Moonshot AI's own cached rate is $0.60/M, so the discount applies on top of a rate that is already below official. Nothing has to be set on the request; the prefix is matched automatically. On an agent loop, where most of every request is unchanged from the last one, this is usually the largest single line on the bill.
How do I call Kimi K3 from my code?
Point an OpenAI SDK at https://router.xark.io/api/v1 and pass model="moonshotai/kimi-k3" — the chat completions endpoint is https://router.xark.io/api/v1/chat/completions. Request shape, streaming frames, the usage block and the error envelope all match what your OpenAI client already handles, so the base URL and the model id are the only two lines that change. The bare name kimi-k3, without the provider prefix, resolves to the same model. An integration written before the ids were namespaced therefore keeps working.
How large is Kimi K3's context window?
512K — 524,288 tokens in a single request, shared between everything you send and everything the model generates back. For comparison, the widest context in this catalogue is Llama 4 Maverick at 1M. Context is billed like any other input: filling the window costs the input rate on every token in it, every turn, which is why the cached-input rate matters more than the window size on a workload that resends the same prefix.
What licence is Kimi K3 under, and can I use it commercially?
Kimi K3 is published by Moonshot AI under the Modified MIT licence. That is a standard permissive text with publisher-specific modifications, and the modifications are the entire reason for the qualifier — so we will not summarise them from the name. The base terms allow commercial use, modification and redistribution with the notices preserved; whether Moonshot AI's changes narrow any of that for your deployment is a question the licence text answers and this page cannot. Read it before you ship anything that depends on the answer.
How does Kimi K3 pricing here compare with other providers carrying it?
Of the 2 other providers we track carrying Kimi K3, the lowest is DeepInfra at $2.40/M input and $11.50/M output, against our $1.85/M input and $9.00/M output. That is where the rates stood when we last reconciled them, and it can change without notice — we are not claiming to be the cheapest source for this model, only that our rate sits below Moonshot AI's official $3.00/M. If you find one of these figures stale, tell us and we will correct it.
What is Kimi K3 actually good at?
The current open-weight frontier. Half-million-token context and frontier-class reasoning, at roughly a fifth of what closed models charge for the same work. In practice that points at whole-codebase reasoning without a retrieval layer, research synthesis over hundreds of documents and complex multi-step planning agents. The specifics that actually decide a fit — the rate, the licence and what it will and will not serve today — are all on this page rather than behind a sales conversation.