model apis · chat / llm
Run Kimi K3 by Moonshot AI through one OpenAI-compatible endpoint. Included in the $0.99-a-month flat plan, or pay per use against your deeprelay balance. No instance to rent, no deployment to manage.
Available nowIncluded in the $0.99/month flat plan. The plan carries 500 million input and 50 million output tokens a month across the included models, weighted by each model's usage factor. The rates below are what Kimi K3 costs pay as you go, and what a request bills once a month's allowance is spent.
Live catalog rates, billed per use against your deeprelay balance, no minimums.
| Tier | Rate |
|---|---|
| Serverless | Input tokens: $1.95 / 1MCached input tokens: $0.195 / 1MOutput tokens: $9.75 / 1M |
rates are read every few minutes from the live model catalog and metered per request
Last 7 days · as of UTC
Any OpenAI SDK works: set the base URL to https://api.deeprelay.ai/v1 and use your deeprelay API key.
curl https://api.deeprelay.ai/v1/chat/completions \
-H "Authorization: Bearer $DEEPRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deeprelay/kimi-k3",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.deeprelay.ai/v1",
api_key="YOUR_DEEPRELAY_API_KEY",
)
response = client.chat.completions.create(
model="deeprelay/kimi-k3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.deeprelay.ai/v1",
apiKey: process.env.DEEPRELAY_API_KEY,
});
const response = await client.chat.completions.create({
model: "deeprelay/kimi-k3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);| Model id | deeprelay/kimi-k3 |
| Modality | Chat / LLM |
| Author | Moonshot AI |
| Context window | 1,048,576 tokens |
| Streaming | Supported |
| Aliases | – |
| Flat plan | Included ($0.99/month) |
faq
Kimi K3 is included in deeprelay's flat plan: $0.99 a month covers 500 million input and 50 million output tokens a month across the included models. Pay as you go, it costs $1.95 / 1M (input tokens), $0.195 / 1M (cached input tokens), $9.75 / 1M (output tokens), billed against your deeprelay balance, the same rates that apply once a month's allowance is spent. No minimums either way.
Yes. Kimi K3 is one of the models the flat plan covers: $0.99 a month carries 500 million input and 50 million output tokens a month, weighted by each model's published usage factor. Requests past the allowance (and any model outside the plan) bill pay as you go at the listed rates.
Yes. Point any OpenAI SDK at https://api.deeprelay.ai/v1 with a deeprelay API key and request model "deeprelay/kimi-k3". No proprietary client needed.
Kimi K3 supports a 1,048,576-token context window on deeprelay.
Chat models bill per input and output token at the listed per-million-token rates, metered per request against your deeprelay balance. Where a cached-input rate is listed, the part of a prompt the serving partner answers from its prompt cache (reported as prompt_tokens_details.cached_tokens) bills at that lower rate instead of the input rate. On the $0.99-a-month flat plan, requests to Kimi K3 draw on the plan's monthly token allowance first and only bill your balance once it is spent.