MarketSupport← Back to app

Kimi

Kimi chat models are called through one simple endpoint: send a messages array plus the model slug and get the reply text back. This family exposes 2 models.

Overview

Send a standard messages array (user / assistant / system roles). Billing is deducted from your credit balance per response; the response includes your remaining balance.

Authentication

Create an API key at /api-keys, then send it as a Bearer token. Requests from the browser while logged in also work via the session cookie.

Authorization: Bearer <YOUR_API_KEY>

OpenAI-compatible Chat Completions

POST
POST https://api.lithovas.com/v1/chat/completions

Use this endpoint for developer integrations: point your OpenAI SDK base_url to https://api.lithovas.com/v1 and send a Lithovas API key.

Kimi K3
Kimi K3 is connected to Lithovas through OpenRouter. Use model: "chat/kimi-k3"; /v1/chat/completions also accepts the OpenRouter upstream model id moonshotai/kimi-k3. OpenRouter currently lists Kimi K3 as text, image, and video input to text output; Lithovas currently supports text plus image image_url content parts, with public HTTPS URLs and data:image/...;base64,... accepted.
Python SDK
Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_LITHOVAS_API_KEY",
    base_url="https://api.lithovas.com/v1",
)

completion = client.chat.completions.create(
    model="chat/kimi-k3",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

print(completion.choices[0].message.content)
cURL
cURL
curl -X POST https://api.lithovas.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "chat/kimi-k3",
    "messages": [
      { "role": "system", "content": "You are a helpful assistant." },
      { "role": "user", "content": "Hello!" }
    ]
  }'
Kimi K3 image input
Python
from openai import OpenAI
import base64

client = OpenAI(
    api_key="YOUR_LITHOVAS_API_KEY",
    base_url="https://api.lithovas.com/v1",
)

image_url = "https://example.com/photo.jpg"

# Alternative: local image as Base64 Data URL.
# with open("photo.png", "rb") as f:
#     image_url = f"data:image/png;base64,{base64.b64encode(f.read()).decode('utf-8')}"

completion = client.chat.completions.create(
    model="chat/kimi-k3",
    messages=[{
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": image_url}},
            {"type": "text", "text": "请描述这张图片，并指出重要细节"},
        ],
    }],
)

print(completion.choices[0].message.content)

Chat Completions

POST
POST https://api.lithovas.com/api/chat

Body: { "model": "<slug>", "messages": [{ "role": "user", "content": "…" }] }

Response: { "text": "<assistant reply>", "credits": <billed>, "balance": <remaining> }

Models

ModelProvidermodel slug
Kimi K3Moonshotchat/kimi-k3
Kimi K2.6Moonshotchat/kimi-k2-6

Kimi K3

POST/v1/chat/completions
cURL
curl -X POST https://api.lithovas.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "chat/kimi-k3",
    "messages": [{
      "role": "user",
      "content": [
        { "type": "text", "text": "Describe this image." },
        { "type": "image_url", "image_url": { "url": "https://example.com/photo.jpg" } }
      ]
    }]
  }'

Kimi K2.6

POST/v1/chat/completions
cURL
curl -X POST https://api.lithovas.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "chat/kimi-k2-6",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'