Chat Completions

Generate text responses from any supported model using the OpenAI-compatible chat completions endpoint.

Endpoint

POST https://api.aihubspot.app/v1/chat/completions

Fully OpenAI-compatible. Use the OpenAI SDK by setting base_url to https://api.aihubspot.app/v1.

Request body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g. `gpt-4o`, `claude-3-5-sonnet`)
`messages`	array	Yes	Array of message objects
`stream`	boolean	No	Enable SSE streaming (default: false)
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	number	No	Sampling temperature 0–2

Example

from openai import OpenAI
 
client = OpenAI(
    api_key="AH_SMKRPA_YOUR_KEY",
    base_url="https://api.aihubspot.app/v1",
)
 
response = client.chat.completions.create(
    model="claude-3-5-sonnet",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

import OpenAI from 'openai';
 
const client = new OpenAI({
  apiKey: process.env.AH_API_KEY,
  baseURL: 'https://api.aihubspot.app/v1',
});
 
const response = await client.chat.completions.create({
  model: 'claude-3-5-sonnet',
  messages: [{ role: 'user', content: 'Hello' }],
});
console.log(response.choices[0].message.content);

curl https://api.aihubspot.app/v1/chat/completions \
  -H "Authorization: Bearer $AH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"claude-3-5-sonnet","messages":[{"role":"user","content":"Hello"}]}'

Streaming

with client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True,
) as stream:
    for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

const stream = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true,
});
 
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '');
}

Drop-in replacement for the OpenAI API. Any library or framework that works with OpenAI works here — just change base_url.