NezhaGateNezhaGate
Chat

GPT-6.1 Sol

⧉
gpt-6.1-sol
Model Type Astra6.1 SolSolLuna

GPT-6.1 Sol is the GPT-6 Sol upgrade OpenAI released on September 29, 2026. OpenAI says it comes close to GPT-6 Astra on agentic coding, computer use and professional work, at one fifth of Astra's list price. It has a 1,050,000-token context, up to 128,000 output tokens, reasoning_effort in five steps (low / medium / high / xhigh / max), image input and tool calling. Fully OpenAI-SDK compatible - set model to gpt-6.1-sol - and served on both /chat/completions and /responses. Pay-as-you-go, failed calls never billed; cached input bills at one tenth, and we do not add the long-context surcharge the official API applies.

ChatGPT-6 familyAgentic coding1.05M contextPrompt caching

Live Test · Playground

Try out GPT-6.1 Sol right here (available after login).

Input

Advanced

This model is served over a ChatGPT-subscription upstream that does not accept temperature / top_p / max_tokens (they are silently ignored). Use reasoning_effort below for thinking depth, and prompt wording for length.

Web search
Memory · multi-turn

Conversation

Start a conversationType a message below to begin

About GPT-6.1 Sol

GPT-6.1 Sol is the GPT-6 Sol upgrade OpenAI announced at DevDay on September 29, 2026, served on NezhaGate through the OpenAI-compatible API. OpenAI says it comes close to GPT-6 Astra on agentic coding, computer use and professional work, at one fifth of Astra's list price. It has a 1,050,000-token context, up to 128,000 output tokens per call, reasoning_effort in five steps (low / medium / high / xhigh / max), image input and tool calling, on both /chat/completions and /responses. Set model to gpt-6.1-sol and keep your SDK and request shape. Pay-as-you-go, failed calls are never billed, and cached input settles at one tenth of the input rate.

Use cases

Near-Astra coding

Multi-file refactors, cross-module debugging, whole features written from a spec: coding work that needs sustained reasoning goes to 6.1 Sol for a fraction of what Astra costs.

Agentic workflows

Codex, Cursor and Claude Code speak the OpenAI-compatible endpoint, so switching to GPT-6.1 Sol is a one-field change to model, with tool calls returned in the OpenAI format.

Professional documents and analysis

Report writing, spreadsheet and data analysis, long-document review: professional work is one of the areas where OpenAI says it comes close to Astra.

Long-context engineering

1,050,000 tokens holds a whole repository plus its docs in one call, with no chunking and stitching of your own.

How to choose

Pick GPT-6.1 Sol when you want near-Astra coding and agent work at a controlled cost; keep GPT-6 Astra for the hardest reasoning, and use GPT-6 Luna for simple high-volume, low-latency work. They all belong to the GPT-6 family and share a 1,050,000-token context, so switching is a one-field change.

FAQ

How is it different from GPT-6 Sol?
GPT-6.1 Sol is the upgrade to GPT-6 Sol; OpenAI says it comes close to GPT-6 Astra on agentic coding, computer use and professional work. The effort ladder differs too: GPT-6.1 Sol starts at low and has no none or minimal level (send either and the gateway treats it as low instead of returning an error).
How does it compare with GPT-6 Astra?
Astra is still the most capable GPT-6 flagship, for the hardest reasoning and research-grade work. OpenAI says GPT-6.1 Sol comes close to it on those three kinds of work at one fifth of Astra's list price; context and integration are identical.
Which reasoning_effort levels are supported?
Five: low / medium / high / xhigh / max. The upstream rejects none and minimal, so the gateway maps both to low. When omitted the gateway requests medium, the model's own default, and returns the thinking summary; more thinking means more output tokens, billed at actual usage.
What are the context, output and knowledge limits?
A 1,050,000-token context window and up to 128,000 output tokens per call; OpenAI gives April 30, 2026 as the knowledge cutoff. System-prompt overhead counts toward the context window.
Can I use /v1/responses?
Yes. The same model name works on /v1/chat/completions and /v1/responses, and both endpoints support streaming.
Am I charged for failed calls?
No. Only calls that return a proper response are settled at actual usage; upstream errors and timeouts never touch your balance.

Related Models

Explore other models you can integrate.

View all →