GPT-6 Sol API in India

GPT-6 Sol is OpenAI's model built for complex coding and agentic workflows, and it is live on unoblox as openai/gpt-6-sol: one OpenAI-compatible endpoint, one key, and rupee billing with a GST invoice.

What GPT-6 Sol is

OpenAI released GPT-6 Sol on 22 September 2026 as the capable end of a pair, alongside the smaller GPT-6 Luna. 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 that can be set from none up to max (medium is the default). Its stated knowledge cutoff is 20 April 2026. OpenAI's own endpoint also accepts image input; on unoblox the model is listed for text in, text out.

In practice Sol is the model you reach for when a task is long, multi-step and expensive to get wrong: working through a large codebase, running a tool-using agent for many turns, or reasoning over a long specification.

Where it fits

• Coding agents that read many files, plan a change and call tools across dozens of turns.
• Long-document work such as comparing contracts or specifications that fit inside a very large context window.
• Hard reasoning steps inside a pipeline where a cheaper model hands off the difficult cases.

Pick Sol when quality on a hard task matters more than per-token price. For high-volume, narrower jobs, GPT-6 Luna in the same family costs a small fraction per token. Because both sit behind the same key, routing easy requests to Luna and hard ones to Sol is a change to one string.

₹ pricing for GPT-6 Sol

On unoblox, GPT-6 Sol costs ₹192.57 per million input tokens and ₹962.83 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 ₹19.26 per million. The model's context length on unoblox is 1,050,000 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
GPT-6 Sol	₹192.57	₹962.83
GPT-6 Luna	₹9.63	₹48.14
GPT-6.1 Sol	₹192.57	₹962.83
GPT-6 Astra	₹962.83	₹4,814.13

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹7,702.72 on GPT-6 Sol (₹3,851.40 for input plus ₹3,851.32 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling GPT-6 Sol 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-sol",
    "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-sol",
    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 Sol 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 Sol available in India on unoblox? Yes. Call openai/gpt-6-sol on https://api.unoblox.ai/v1 with your unoblox key. Usage is billed in rupees against your wallet.

How large is the context window? unoblox lists a context length of 1,050,000 tokens for this model.

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

Can I change temperature? No. These models run at their default temperature, so omit the field.

What is the difference between GPT-6 Sol and GPT-6.1 Sol? GPT-6.1 Sol is the newer release, positioned by OpenAI as near its top GPT-6 Astra tier at a lower cost. Both are on unoblox; compare them on your own prompts.

Does using Sol keep my data in India? No. Inference happens at the model provider. unoblox is India-billed with a GST invoice, but we do not claim data residency for this model.

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