GPT-6 Luna API in India

GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks, available on unoblox as openai/gpt-6-luna. It gives Indian teams a small-footprint model with a very large context window, billed in rupees on a GST invoice.

What GPT-6 Luna is

OpenAI released Luna on 22 September 2026 alongside GPT-6 Sol. OpenAI documents a 1.05 million-token context window, up to 128,000 output tokens, streaming, structured outputs, function calling and prompt caching, with reasoning effort selectable from none to max (medium by default). Its stated knowledge cutoff is 18 May 2026. unoblox lists it for text in and text out.

Luna's pitch is throughput and price: the same family and API shape as Sol, aimed at jobs where you run many requests and each one is relatively well defined.

Where it fits

• Classification and routing of tickets, emails and documents at volume.
• Structured extraction into JSON from invoices, forms and call transcripts.
• First-pass drafting and summarisation where a stronger model reviews only the hard cases.

Use Luna as the default for volume, then escalate to GPT-6 Sol or GPT-6.1 Sol for the requests that need deeper reasoning. Since reasoning effort is adjustable, you can also keep it low for simple calls and raise it only where accuracy needs it.

₹ pricing for GPT-6 Luna

On unoblox, GPT-6 Luna costs ₹9.63 per million input tokens and ₹48.14 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. Cached input tokens are listed at ₹0.96 per million. The model's context length on unoblox is 1,050,000 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
GPT-6 Luna	₹9.63	₹48.14
GPT-6 Sol	₹192.57	₹962.83
GPT-5 mini	₹24.07	₹192.57
GPT-4.1 mini	₹38.51	₹154.05

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹385.16 on GPT-6 Luna (₹192.60 for input plus ₹192.56 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling GPT-6 Luna from the unoblox endpoint

unoblox is OpenAI-compatible, so any OpenAI SDK works by changing the base URL and key.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_UNOBLOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-luna",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}],
    "max_tokens": 512
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_UNOBLOX_API_KEY",
    base_url="https://api.unoblox.ai/v1",
)
resp = client.chat.completions.create(
    model="openai/gpt-6-luna",
    messages=[{"role": "user", "content": "Summarise this support ticket in two lines."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

Get a key at https://unoblox.ai/sign-in and top up your wallet in rupees.

Notes on parameters, billing and data

Cap output with max_tokens; unoblox also accepts OpenAI's max_completion_tokens for the same purpose. On a reasoning model the limit includes reasoning tokens, so set it high enough to leave room for the visible answer. GPT-6 Luna runs at its default temperature, so leave temperature out of your request. Prompts above 272K input tokens are billed at a higher long-context rate, shown on the model page. The model runs at its provider rather than on unoblox hardware, so do not assume the data stays in India. unoblox provides rupee pricing, a GST invoice and a single endpoint.

Frequently asked questions

Is GPT-6 Luna available in India? Yes, as openai/gpt-6-luna on https://api.unoblox.ai/v1, billed in rupees.

What is Luna best for? High-volume, focused work such as extraction, classification and routing, per OpenAI's description of the model.

How big is the context window? unoblox lists 1,050,000 tokens.

Which output-limit parameter do I use? Send max_tokens; max_completion_tokens is accepted too. Reasoning tokens count toward the limit.

Can I mix Luna and Sol in one app? Yes. Both are behind the same key, so you can route by task difficulty by changing the model string.

Is there a GST invoice? Yes. Usage across all models is covered by a GST invoice from unoblox.

Is there a different price for very long prompts? Yes. Prompts above 272K input tokens are billed at a higher long-context rate, shown on the model page.

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