One API key, every major LLM. OpenAI-compatible — just swap base_url and you're talking to Turing.
curl https://live-turing.cn.llm.tcljd.com/api/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $TURING_API_KEY" \
-d '{
"model": "turing/gpt-5.4-mini",
"messages": [
{"role": "user", "content": "你好,请用一句话介绍自己"}
]
}'
from openai import OpenAI
client = OpenAI(
api_key="your-api-key",
base_url="https://live-turing.cn.llm.tcljd.com/api/v1",
)
response = client.chat.completions.create(
model="turing/gpt-5.4-mini",
messages=[{"role": "user", "content": "你好,请用一句话介绍自己"}],
)
print(response.choices[0].message.content)
import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
OpenAIClient client = OpenAIOkHttpClient.builder()
.apiKey("your-api-key")
.baseUrl("https://live-turing.cn.llm.tcljd.com/api/v1")
.build();
ChatCompletion completion = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("turing/gpt-5.4-mini")
.addUserMessage("你好,请用一句话介绍自己")
.build()
);
System.out.println(completion.choices().get(0).message().content());
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "your-api-key",
baseURL: "https://live-turing.cn.llm.tcljd.com/api/v1",
});
const response = await client.chat.completions.create({
model: "turing/gpt-5.4-mini",
messages: [{ role: "user", content: "你好,请用一句话介绍自己" }],
});
console.log(response.choices[0].message.content);
Quick Start
Create an API key, configure your base URL, make your first call
Models
All available models — capabilities, context, pricing, regions
API Reference
Chat / Embeddings / Images schemas with Try-It
Billing & Usage
Token / cache / search billing dimensions, service_usages, trace-level reconciliation
AI Coding Tools
Claude Code / Codex / OpenCode / Claude for Office
Enterprise Onboarding
Enterprise API onboarding — application, service agreement, quota scaling