GPT-6.1 Sol API in India

GPT-6.1 Sol is OpenAI's refresh of Sol, described by OpenAI as near-Astra performance for complex work at a lower cost. It is live on unoblox as openai/gpt-6.1-sol, billed in rupees with a GST invoice.

What GPT-6.1 Sol is

OpenAI released GPT-6.1 Sol on 29 September 2026 and positions it for complex coding, computer use and professional work. Documented specs include a 1.05 million-token context window, up to 128,000 output tokens, streaming, structured outputs, function calling and prompt caching. Reasoning effort runs from low to max with medium as the default; the none and minimal settings are not supported. Its stated knowledge cutoff is 30 April 2026.

For a launch write-up with a comparison against GPT-6 Sol and Astra, see our GPT-6.1 Sol launch post.

Where it fits

• Software engineering tasks where the model must reason across a module, explain a failure and propose a tested fix.
• Professional analysis that turns long source material into a structured report or decision brief.
• Agent backbones that need strong planning and tool use over a long session.

Choose GPT-6.1 Sol over GPT-6 Sol when you want the newer release for demanding work. Keep GPT-6 Astra in view for the very hardest tasks, and use Luna for bulk work. Run your own prompts through each, since task results vary.

₹ pricing for GPT-6.1 Sol

On unoblox, GPT-6.1 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 ₹9.63 per million. The model's context length on unoblox is 1,050,000 tokens.

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

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹7,702.72 on GPT-6.1 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-6.1 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-6.1-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-6.1-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-6.1 Sol runs at its default temperature, so leave temperature out of your request. Reasoning effort cannot be set to none or minimal on this model. 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-6.1 Sol live on unoblox? Yes, as openai/gpt-6.1-sol on https://api.unoblox.ai/v1.

What are its reasoning levels? OpenAI documents low, medium (default), high, xhigh and max. None and minimal are not available.

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

What is its knowledge cutoff? OpenAI states 30 April 2026.

Do I get a GST invoice? Yes. Usage is invoiced in rupees with GST.

Is my data processed in India? Not necessarily. The model runs at its provider, and we do not claim data residency for it.

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