Kimi K3 (moonshot/kimi-k3) is priced at $3.00/M input and $15.00/M output tokens through AIgateway. 1,048,576-token context window. AIgateway charges pass-through on the underlying Moonshot rate, with no monthly minimum. Add a card (no charge) for $1 in credit across a curated trial catalog led by GLM-5.2.
AIgateway bills at the same per-token rate Moonshot publishes. There's no inflated sticker price; the model-vendor's invoice and your gateway invoice agree on the token count and unit cost. Usage is aggregated to the nearest fraction of a cent in D1 and surfaced live in your dashboard.
The only margin on top is a flat 5% platform fee, added to the provider cost on every API call. Cached requests (when you use prompt caching or semantic cache) get a 50% discount on the uncached cost, so long-context agent workloads often run net cheaper than calling Moonshot directly. A separate 5% covers card processing when you top up — shown before you pay.
No subscription and no monthly minimum. A payment method is required to call the API — adding a card is free, never charges you, and grants $1 in credit across a curated trial catalog of 15 models led by GLM-5.2. The $1 expires 30 days after you add the card. Top up from $5 with no auto-renew to unlock the full catalog — topups never expire. BYOK (bring your own Moonshot key) is supported on Enterprise if you already have a direct contract you want to preserve.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
r = client.chat.completions.create(
model="moonshot/kimi-k3",
messages=[{"role": "user", "content": "Explain vector databases in two sentences."}],
)
print(r.choices[0].message.content)// npm i aigateway-js openai
// aigateway-js: sub-accounts, evals, replays, jobs, webhook verify.
// openai SDK: chat/embeddings/images/audio — drop-in compat.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.aigateway.sh/v1",
apiKey: process.env.AIGATEWAY_KEY,
});
const r = await client.chat.completions.create({
model: "moonshot/kimi-k3",
messages: [{ role: "user", content: "Explain vector databases in two sentences." }],
});
console.log(r.choices[0].message.content);Input is $3/M tokens, output is $15/M tokens. A typical 1K-in / 500-out chat turn costs about $0.01050.
Kimi K3 is not on the $1 card-credit trial catalog — that credit covers 15 curated picks led by GLM-5.2. The full catalog starts at a $5 top-up.
Not natively. AIgateway's semantic cache can still hit duplicate prompts and gives a 50% discount on cached requests.
Pass-through pricing means you automatically get whatever tier discount Moonshot publishes. AIgateway doesn't mark up; the 5% platform fee applies flat regardless of volume. Enterprise customers can negotiate committed-use discounts on top.
Every call returns usage.prompt_tokens and usage.completion_tokens in the response body, same as OpenAI. We also write the exact cost into x-aigateway-cost response header. Full audit log is in the dashboard.