APIリファレンス

POST /v1/chat/completions
Content-Type: application/json
Authorization: Bearer sk-silk-xxxxxxxxxxxx

{
  "model": "luxeno/glm-4-flash",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user",   "content": "Explain quantum entanglement in one sentence." }
  ],
  "temperature": 0.7,
  "max_tokens": 256
}

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1748000000,
  "model": "luxeno/glm-4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum entanglement is a phenomenon where two particles become correlated such that measuring one instantly determines the state of the other, regardless of distance."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 38,
    "total_tokens": 69
  }
}

POST /v1/chat/completions
Content-Type: application/json
Authorization: Bearer sk-silk-xxxxxxxxxxxx

{
  "model": "luxeno/glm-4-flash",
  "messages": [{ "role": "user", "content": "Count to five." }],
  "stream": true
}

--- SSE response ---
data: {"id":"chatcmpl-xyz","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant","content":"1"},"index":0}]}

data: {"id":"chatcmpl-xyz","object":"chat.completion.chunk","choices":[{"delta":{"content":", 2"},"index":0}]}

data: {"id":"chatcmpl-xyz","object":"chat.completion.chunk","choices":[{"delta":{},"finish_reason":"stop","index":0}],"usage":{"prompt_tokens":12,"completion_tokens":10}}

data: [DONE]

POST /v1/messages
Content-Type: application/json
Authorization: Bearer sk-silk-xxxxxxxxxxxx
anthropic-version: 2023-06-01

{
  "model": "claude-sonnet-4-20250514",
  "max_tokens": 1024,
  "system": "You are a concise technical writer.",
  "messages": [
    { "role": "user", "content": "What is a B-tree index?" }
  ]
}

{
  "id": "msg_01AbCdEf",
  "type": "message",
  "role": "assistant",
  "content": [
    {
      "type": "text",
      "text": "A B-tree index is a balanced tree data structure that maintains sorted data and allows searches, insertions, deletions, and range queries in O(log n) time."
    }
  ],
  "model": "claude-sonnet-4-20250514",
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 24,
    "output_tokens": 42
  }
}

data: {"type":"message_start","message":{"id":"msg_01AbCd","type":"message","role":"assistant","usage":{"input_tokens":24,"output_tokens":0}}}

data: {"type":"content_block_start","index":0,"content_block":{"type":"text","text":""}}

data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"A B-tree index"}}

data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":" is a balanced tree..."}}

data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":42}}

data: {"type":"message_stop"}

from anthropic import Anthropic

# Anthropic SDK appends /v1/messages internally — set base_url WITHOUT /v1
client = Anthropic(
    api_key="sk-silk-...",
    base_url="https://api.luxeno.ai",
)

msg = client.messages.create(
    model="claude-haiku-4-5-20251001",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)

from openai import OpenAI

# OpenAI SDK requires base_url to INCLUDE /v1
client = OpenAI(
    api_key="sk-silk-...",
    base_url="https://api.luxeno.ai/v1",
)

resp = client.chat.completions.create(
    model="luxeno/glm-4-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: "sk-silk-...",
  baseURL: "https://api.luxeno.ai",
});

const msg = await client.messages.create({
  model: "claude-haiku-4-5-20251001",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(msg.content[0].text);

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-silk-...",
  baseURL: "https://api.luxeno.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "luxeno/glm-4-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

HTTP/1.1 429 Too Many Requests
Retry-After: 12
Content-Type: application/json

{
  "error": {
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "code": 429
  }
}