OpenAI SDK, India endpoint

The OpenAI SDK is everywhere (Python, Node.js, Go, Java). unoblox replaces OpenAI with a simple two-line config swap: one endpoint, one key, one ₹ invoice. No code rewrite.

Why OpenAI SDK + unoblox

• Tiny change: only api_key + base_url differ
• No SDK fork: you use the official OpenAI SDK
• All features: streaming, tools, JSON mode, vision — all pass-through
• 40+ models: all via one endpoint
• ₹ billing: monthly GST invoice from India

Python setup (2 lines)

from openai import OpenAI

# Two config lines
client = OpenAI(
    api_key="ub-gw-YOUR_API_KEY",
    base_url="https://api.unoblox.ai/v1"
)

# Now use it normally
response = client.chat.completions.create(
    model="openai/gpt-4o",  # Or any unoblox model
    messages=[
        {"role": "user", "content": "Explain RAG in 2 sentences."}
    ]
)
print(response.choices[0].message.content)

Node.js setup (2 lines)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.UNOBLOX_API_KEY,
  baseURL: 'https://api.unoblox.ai/v1'
});

const message = await client.chat.completions.create({
  model: 'openai/gpt-4o',
  messages: [{ role: 'user', content: 'Say hello in Hindi.' }]
});

console.log(message.choices[0].message.content);

Streaming example (Python)

stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku."}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Tool use (JSON mode)

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "What's the weather?"}],
    tools=[
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "parameters": {"type": "object", "properties": {}}
            }
        }
    ]
)
print(response.choices[0].message.tool_calls)

Model pricing (same endpoint)

Model	₹ input	₹ output	Use case
Qwen3 1.7B	FREE	FREE	agents, prototyping
DeepSeek V4 Flash	₹9.07	₹18.14	budget inference
GPT-4o	₹252	₹1008	complex tasks
Claude Opus	₹504	₹2520	reasoning

Frequently asked questions

Can I keep my existing OpenAI code? Yes. Only change api_key and base_url. Everything else — method calls, parameter names — stays the same.

Does every OpenAI feature work with unoblox? Most do. Check model pages in /models for per-model feature support — some models lack vision or tools.

How do I switch models at runtime? Just change the model parameter in each .create() call. No client reconfiguration needed.

What if I need to fall back to OpenAI? Swap api_key and base_url in your config (env vars help here). No code change, just a runtime config switch.

Does async work? Yes. Use AsyncOpenAI instead of OpenAI, then await calls inside async functions — including with stream=True for async streaming.

Can I batch requests? unoblox doesn't offer an OpenAI-style batch endpoint yet. Loop individual requests instead — each is billed at the normal per-token rate.

Get started in rupees → https://unoblox.ai/sign-in