GPT-6.1 Sol
OpenAI releases GPT-6.1 Sol
On September 29th, OpenAI released GPT-6.1 Sol, a model for complex coding, computer use and professional work. It's in the API, through the Responses and Chat Completions endpoints.
What it is
GPT-6.1 SolWhat the model is.
Close to Astra, for less
GPT-6.1 SolOpenAI says it comes close to Astra for less money
OpenAI's advice is to compare the two on your own tasks.
OpenAI describes GPT-6.1 Sol as near-Astra performance at a lower cost, which is OpenAI's own claim. Its advice is to run both on your own tasks and weigh quality against price.
The middle of the GPT-6 family
GPT-6.1 SolGPT-6.1 Sol is now the middle of the GPT-6 family
It takes the middle spot that GPT-6 Sol held a week ago. Astra is for the hardest work, Sol balances speed, cost and intelligence, and Luna is the fast, cheap one.
A million-token context
GPT-6.1 SolText and images in, text out, with a million-token context
It takes text and images and writes text. The context window holds about a million tokens, one reply can run to 128,000 tokens, and its knowledge stops at April 30th, 2026.
What it costs
GPT-6.1 SolWhat it costs.
A fifth of Astra's price
GPT-6.1 SolGPT-6.1 Sol costs a fifth of Astra per token
Per million tokens, GPT-6.1 Sol costs 2 dollars in and 10 dollars out. Astra costs 10 and 50, so OpenAI puts Sol at one fifth of Astra's standard prices.
Cached input at half the old rate
GPT-6.1 SolCached input costs half what it did on GPT-6 Sol
The list prices match GPT-6 Sol, but repeated context got cheaper. Cached input was 20 cents per million tokens. On GPT-6.1 Sol it's 10 cents, 5 percent of the normal input price.
Batch, Flex, Fast and long prompts
GPT-6.1 SolThe price moves with how you run it
Batch and Flex processing cost half. Fast mode costs double. And a prompt over 272,000 input tokens doubles the input price and adds half to the output price, for the whole request.
Multi-agent, in beta
GPT-6.1 SolMulti-agent, in beta.
Subagents in one request
GPT-6.1 SolGPT-6.1 Sol can hand work to subagents in one request
Multi-agent, in beta in the Responses API
GPT-6.1 Sol supports Multi-agent, in beta. In one Responses API request, the model spins up subagents, runs them in parallel, and combines their work into one answer. Among GPT-6 models, the guide lists only Sol.
When subagents help
GPT-6.1 SolSubagents suit work that splits into independent pieces
OpenAI suggests it for work that splits cleanly, like separate parts of a big codebase. It helps less when each step depends on the last. Subagents can raise token use, and the beta's schemas may change.
Who can use it
GPT-6.1 SolWho can use it, and how.
API usage tiers
GPT-6.1 SolThe API's free tier can't use GPT-6.1 Sol
On the API's free tier, GPT-6.1 Sol isn't supported. Usage tier 1 starts at 500 requests a minute. Tier 5 reaches 15,000 requests and 40 million tokens a minute.
US and EU data residency
GPT-6.1 SolUS and EU data residency, without Fast mode in the EU
Regional processing adds 10% where it's available.
GPT-6.1 Sol supports US and EU data residency, but Fast mode is unavailable with EU residency. Regional processing adds 10 percent to the price where it's available.
Tool calling needs Responses
GPT-6.1 SolTool calling needs the Responses API
For tool calling, use the Responses API, where Sol gets web search, file search, computer use, MCP and more. Chat Completions works only without tools. GPT-6 Sol allowed function calls there with reasoning turned off.
Reasoning starts at low
GPT-6.1 SolReasoning effort now starts at low
The none and minimal settings aren't supported.
Reasoning effort runs from low, through medium, the default, up to max. The none and minimal settings aren't supported. On GPT-6 Sol, none was available.
Switching from GPT-6 Sol
GPT-6.1 SolMoving from GPT-6 Sol? Read OpenAI's migration guidance first
developers.openai.com › Using GPT-6 › Migration quickstart
If you already use GPT-6 Sol, OpenAI asks you to review its migration guidance before switching. It's in the Using GPT-6 guide, on OpenAI's developer site.
