Kimi K3 is Moonshot's flagship reasoning model with a 1M token context, always-on thinking, native web search, and text, image, and video inputs.
Moonshot AIText Generation1M contextReleased Jul 15, 2026InternationalProprietary EndpointNewKimi K3 is Moonshot's flagship reasoning model with a 1M token context, always-on thinking, native web search, and text, image, and video inputs.
Supports text, image, and video inputs, function calling, JSON schema structured output, and built-in web search billed at $0.015 per invoked call. Thinking is always on with a tunable reasoning_effort control (max recommended); reasoning tokens are billed as output tokens. Temperature and other sampling overrides are fixed by the model service. Multi-step function calling must replay the assistant message with its reasoning_content field intact. Explicit cache controls, batches, and fine-tuning are not supported.
Also known as Moonshot AI Kimi K3, Kimi-K3
kimi-k3/v1/chat/completionsPOST/v1/responsesPOST/v1/messagesPOST/v1beta/models/kimi-k3:generateContentmoonshotai/kimi-k3Live pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Kimi K3 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id kimi-k3. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://api.empiriolabs.ai/v1",
api_key="YOUR_EMPIRIOLABS_API_KEY",
)
response = client.chat.completions.create(
model="kimi-k3",
messages=[{"role": "user", "content": "Write a haiku about the ocean."}],
)
print(response.choices[0].message.content)Request parameters supported by the Kimi K3 API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| max_tokens | number | 32768 | 1 to 1048576 | Maximum output tokens. Reasoning tokens count toward this limit. |
| stop | string | - | - | Up to 4 strings where the model will stop generating further tokens. |
| reasoning_effort | enum | max | low, medium, high, max | Kimi K3 reasoning effort. Thinking is always on. Higher effort spends more reasoning tokens before answering. Max is recommended and the default. |
| tool_web_search | boolean | false | - | Search the web for real-time information. Adds $0.015 to the request cost for each invoked web search call. |
| response_format | enum | - | - | Constrain the output to JSON. Use JSON mode for any valid JSON object, or JSON schema to force output that matches a schema you provide. |
Supports text, image, and video inputs with a 1M token context, function calling, JSON schema structured output, and built-in web search at $0.015 per invoked call. Thinking is always on; reasoning depth is tunable with the reasoning_effort control (max is recommended) and reasoning tokens are billed as output tokens. Temperature and other sampling settings are fixed by the model service. Multi-step function calling through the API must replay the assistant message with its reasoning_content field intact.
When this model invokes built-in tools inside a single request, the response carries a normalized usage.tool_usage map alongside the token counts. Tool counts are already factored into cost_usd and are surfaced for transparency.
On EmpirioLabs, Kimi K3 is billed pay as you go: Input $3.00 per 1M prompt tokens; Output $15.00 per 1M generated tokens; Web search $0.015 per call when invoked. The live rate card on this page always matches what the API charges.
Kimi K3 supports a 1M-token context window with up to 131,072 output tokens per response.
Yes. Kimi K3 serves the OpenAI-compatible Chat Completions API, so existing OpenAI SDKs work by pointing base_url at https://api.empiriolabs.ai/v1 and setting the model id to kimi-k3.
Yes. The EmpirioLabs playground runs Kimi K3 in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Check out our pricing or reach out if you want your own model deployed on our stack.
