Chat Completions API

OpenAI-compatible interface for supported Ling and Ring models.

Chat Completions APILink to section

The chat completions endpoint mirrors OpenAI’s v1/chat/completions contract. Use it to stream or fetch supported Ling and Ring model responses with minimal code changes.

Migration notice: Ling-1T, ling-1t, and inclusionai/ling-1t are retired and rejected. Send one of the exact supported model IDs below.

Endpoint: POST https://ling-1t.ai/api/v1/chat/completions
Auth: Authorization: Bearer <api-key>
Models: Ling-2.6-1T, Ling-2.6-flash, Ring-2.6-1T

Model RatesLink to section

Ling-2.6-1T: $0.08 input and $0.65 output per million compute units
Ling-2.6-flash: $0.05 input and $0.004 output per million compute units
Ring-2.6-1T: $0.08 input and $0.65 output per million compute units

Ring Reasoning EffortLink to section

Only Ring-2.6-1T accepts the optional reasoning object. Its effort value can be high or xhigh. When reasoning is present without an effort, the API uses high. Use xhigh for tasks that need deeper reasoning, with the expectation that it may consume significantly more tokens.

{
  "model": "Ring-2.6-1T",
  "messages": [
    { "role": "user", "content": "Analyze this multi-step scheduling problem." }
  ],
  "reasoning": { "effort": "xhigh" },
  "max_tokens": 2048
}

Sending reasoning to either Ling model, or sending an effort other than high or xhigh, returns a 400 error before the upstream request is made.

Request Example (JSON)Link to section

POST /api/v1/chat/completions HTTP/1.1
Host: ling-1t.ai
Authorization: Bearer LING1T-...
Content-Type: application/json

{
  "model": "Ling-2.6-flash",
  "messages": [
    { "role": "system", "content": "You are a precise financial analyst." },
    { "role": "user", "content": "Summarize Q4 revenue trends for APAC." }
  ],
  "temperature": 0.4,
  "max_tokens": 512,
  "stream": false
}

cURLLink to section

curl https://ling-1t.ai/api/v1/chat/completions \
  -H "content-type: application/json" \
  -H "authorization: Bearer $LING1T_API_KEY" \
  -d '{
    "model": "Ling-2.6-1T",
    "messages": [
      { "role": "system", "content": "You are a precise financial analyst." },
      { "role": "user", "content": "Summarize Q4 revenue trends for APAC." }
    ],
    "temperature": 0.4,
    "max_tokens": 512
  }'

Node.js (TypeScript)Link to section

import fetch from 'node-fetch';

const response = await fetch('https://ling-1t.ai/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    Authorization: `Bearer ${process.env.LING1T_API_KEY}`,
  },
  body: JSON.stringify({
    model: 'Ling-2.6-1T',
    messages: [
      { role: 'system', content: 'You are a precise financial analyst.' },
      { role: 'user', content: 'Summarize Q4 revenue trends for APAC.' },
    ],
  }),
});

const data = await response.json();
console.log(data.choices[0].message?.content);

PythonLink to section

import requests

headers = {
    "Authorization": f"Bearer {API_KEY}",
    "Content-Type": "application/json",
}

payload = {
    "model": "Ling-2.6-1T",
    "messages": [
        {"role": "system", "content": "You are a precise financial analyst."},
        {"role": "user", "content": "Summarize Q4 revenue trends for APAC."}
    ],
    "temperature": 0.4,
    "max_tokens": 512
}

resp = requests.post("https://ling-1t.ai/api/v1/chat/completions", json=payload, headers=headers)
resp.raise_for_status()
print(resp.json()["choices"][0]["message"]["content"])

Streaming ResponsesLink to section

Set stream: true to receive Server-Sent Events (SSE). The data format matches OpenAI’s, enabling drop-in use of existing clients.

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Hello"}}],"model":"Ling-2.6-1T"}

...
data: [DONE]

Usage MetricsLink to section

Responses include token usage in the OpenAI schema (usage.prompt_tokens, usage.completion_tokens). These values feed billing and are visible in the dashboard usage explorer.