GPT-6.2 Sol and Astra, GPT-6.1 Sol vs Terra: Pricing, Specs, and How to Use Them in Slack (2026)

GPT-6.2 Astra and Sol (Nov 17, 2026) and GPT-6.1 Sol vs Terra compared: OpenAI API prices, context window, reasoning effort, and how to use them in Slack.

Short answer: On November 17, 2026, OpenAI released GPT-6.2 Astra and GPT-6.2 Sol, so the newest general-purpose GPT-6 lineup is now GPT-6.2 Astra, GPT-6.2 Sol, GPT-6.1 Terra, and GPT-6 Luna. GPT-6.2 Sol keeps GPT-6.1 Sol's price ($2 per million input tokens, $10 per million output tokens) with a newer knowledge cutoff, and GPT-6.2 Astra costs 20% less than GPT-6 Astra on input and output. GPT-6.1 Terra is still the Terra release at half Sol's price, $1 and $5, for visual reasoning, precise computer use, and clear, natural writing. All of them have a 1,050,000-token context window and up to 128,000 output tokens. If your team wants these models inside Slack or Microsoft Teams, you can choose them in a Runbear agent's model settings.

Disclosure: Runbear is our product. OpenAI facts and prices come from OpenAI's developer documentation as of November 2026 and are linked inline. Check those pages before you plan a budget.

What OpenAI released

GPT-6.2 Astra and Sol are the newest releases in the GPT-6 family; the newest Terra is still GPT-6.1 Terra from October. OpenAI's API changelog shows the order:

  • September 3, 2026: GPT-6 Astra, described as OpenAI's "most capable model, built for the hardest end-to-end work."
  • September 22, 2026: GPT-6 Sol and GPT-6 Luna.
  • September 29, 2026: GPT-6.1 Sol, "for complex coding and professional work at a lower cost than GPT-6 Astra."
  • October 26, 2026: GPT-6.1 Terra, "a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing."
  • November 17, 2026: GPT-6.2 Astra and GPT-6.2 Sol. OpenAI's API changelog says to use Astra "for demanding reasoning and coding tasks" and Sol "for everyday coding and agent workflows."

The family uses tier names (Astra, Sol, Terra, Luna) rather than size suffixes like mini or nano. A tier can move to a new release on its own schedule, which is why the current lineup mixes GPT-6.2 (Astra, Sol), GPT-6.1 (Terra), and GPT-6 (Luna). In its October 7 changelog entry, OpenAI wrote: "We recommend leveraging the GPT-6 model family for production API usage."

What GPT-6.2 Astra and Sol change

OpenAI's model pages for GPT-6.2 Sol and GPT-6.2 Astra describe Sol as "our go-to model for everyday work, from coding to powering agents at scale" and Astra as "our most capable model for your hardest projects, from start to finish." Prices below are per million tokens on the Standard tier, as of November 2026.

GPT-6.2 SolGPT-6.2 Astra
Input$2.00 (same as GPT-6.1 Sol)$8.00 (GPT-6 Astra: $10.00)
Cached input$0.10$0.40 (GPT-6 Astra: $1.00)
Cache writes (30-minute retention)$2.50$10.00
Output$10.00 (same as GPT-6.1 Sol)$40.00 (GPT-6 Astra: $50.00)
Context window1,050,000 tokens1,050,000 tokens
Max output128,000 tokens128,000 tokens
Knowledge cutoffJune 1, 2026 (GPT-6.1 Sol: April 30, 2026)May 18, 2026 (GPT-6 Astra: April 30, 2026)
Reasoning effort noneRejected by the APIRejected by the API

The long-context rule carries over: above 272K input tokens, input and cache rates double and output costs 1.5x for the whole request. Beyond price, OpenAI's GPT-6.2 migration guide lists a few behavior changes worth checking before you switch an integration:

  • Top-level instructions move. "Models starting with GPT-6.2 append top-level instructions after input in the Responses API." For guidance you want cached, the migration guide recommends a developer message as the first input item instead.
  • No none effort. Requests that set reasoning effort to none are rejected; OpenAI's guide says to use low instead.
  • Sampling settings are unsupported. OpenAI's guide says to omit temperature, top_p, and top_logprobs from Responses requests.
  • Shorter answers by default. OpenAI notes outputs are more concise, so recheck any "be concise" lines in your system prompt.
  • Tool calling still requires the Responses API, as with GPT-6.1.

The rest of this article compares GPT-6.1 Sol and GPT-6.1 Terra. GPT-6.1 Sol remains available as a specific version, and Terra has no 6.2 release yet.

Table comparing OpenAI API list prices per 1M tokens: GPT-6.1 Sol $2 input, $0.10 cached input, $10 output, knowledge cutoff April 30, 2026; GPT-6.1 Terra $1 input, $0.05 cached input, $5 output, cutoff June 1, 2026; GPT-6 Sol $2 input, $0.20 cached input, $10 output, cutoff April 20, 2026.

GPT-6.1 Sol vs GPT-6.1 Terra at a glance

Every row below comes from OpenAI's model pages for GPT-6.1 Sol and GPT-6.1 Terra, as of October 2026.

GPT-6.1 SolGPT-6.1 Terra
OpenAI's positioning"Near-Astra performance for complex work at a lower cost""A fast, efficient model for visual reasoning, precise computer use, and clear, natural writing"
Input (per 1M tokens)$2.00$1.00
Cached input$0.10$0.05
Cache writes$2.50$1.25 (30-minute retention) or $2.50 (12-hour retention)
Output (per 1M tokens)$10.00$5.00
Context window1,050,000 tokens (922,000 max input)1,050,000 tokens (922,000 max input)
Max output128,000 tokens128,000 tokens
Knowledge cutoffApril 30, 2026June 1, 2026
Reasoning effortlow, medium (default), high, xhigh, maxnone, low, medium (default), high, xhigh, max
Input and outputText and image in, text outText and image in, text out

Both models list the same Responses API tools, including web search, file search, code interpreter, computer use, and MCP. OpenAI notes that tool calling requires the Responses API. Both also share a long-context rule: prompts with more than 272K input tokens are billed at 2x the input and cache rates and 1.5x the output rate for the whole request.

What changed from GPT-6 Sol

GPT-6.1 Sol is the newer Sol release; GPT-6 Sol still has its own model page. The headline prices are the same, but three details differ:

  • Cheaper cached input. Cached input drops from $0.20 to $0.10 per million tokens, or 5% of the uncached rate instead of a tenth. Agents that reuse a long system prompt or the same documents on every turn benefit the most.
  • No "none" reasoning effort. GPT-6 Sol accepts none through max. The GPT-6.1 Sol page lists low through max. If you relied on none for the fastest replies, GPT-6.1 Terra still supports it.
  • A newer knowledge cutoff. April 30, 2026, up from April 20, 2026.

OpenAI also added an Ultrafast service tier for GPT-6.1 Sol on October 8 (service_tier: "ultrafast"). The model page prices Ultrafast at 6x Standard.

What one request costs

At list API prices, a request with 20,000 input tokens and 1,000 output tokens, none of them cached, costs:

  • GPT-6.1 Sol: 20,000 × $2/1M + 1,000 × $10/1M = $0.05
  • GPT-6.1 Terra: 20,000 × $1/1M + 1,000 × $5/1M = $0.025

The long-context rule changes the math quickly. A Sol request with 300,000 input tokens crosses the 272K line, so the whole request is billed at $4 input and $15 output per million: 300,000 × $4/1M + 1,000 × $15/1M = $1.215, about twice the $0.61 it would cost at the base rate. If an agent searches a knowledge base and sends only the relevant passages, it stays far below that line.

These are OpenAI API prices. Inside Runbear, an agent on Runbear-provided access uses Runbear credits instead, as described below.

Which one should your team pick

OpenAI's own descriptions are the best starting point:

  • GPT-6.1 Sol for multistep work: complex coding, computer use, and professional analysis where the model has to plan and call several tools in a row.
  • GPT-6.1 Terra for writing-heavy work and visual reasoning at half the price: drafting replies, summaries, and status updates, or reading screenshots and technical drawings.
  • A lite tier for lookups. Runbear's agent settings docs note that if an agent mostly answers from a knowledge base, the cheapest tier usually matches the most expensive one on answer quality while consuming a fraction of the credits.

A more capable model is not automatically a better agent. Start with the cheaper tier that fits the job, run the questions your team actually asks, and move up only where the answers fall short.

How to use GPT-6.2 or GPT-6.1 in Slack with your team

When a team wants one agent that everyone in a channel can @mention, with shared instructions, knowledge, and tools, the agent needs to live in Slack. Runbear is a no-code AI agent builder for Slack that lets you pick the model per agent, including GPT-6.2 Astra and Sol and GPT-6.1 Terra. For a fuller comparison with OpenAI's own Slack options, see Runbear vs ChatGPT.

Example Slack thread in a support-escalations channel: a teammate asks the Support agent to summarize the thread and draft a customer reply, and the agent replies in the thread with a three-point summary and a short draft.

Setting it up takes four steps:

  1. Open the agent in Runbear and go to the Settings tab. The Model Selection section on Claude Agent SDK agents offers Claude, GPT, and Gemini models.
  2. Choose GPT Astra, GPT Sol, or GPT Terra. These rows carry a Stable badge; today GPT Astra and GPT Sol follow GPT-6.2 and GPT Terra follows GPT-6.1. To keep the agent on one exact release, such as GPT-6.1 Sol, choose it under Specific version instead.
  3. Connect the agent to Slack from the Chatbots tab and invite the bot to the channels where it should answer. The Slack setup guide walks through the options.
  4. Ask it something. The agent always answers @mentions and direct messages, and replying without an @mention is a separate switch you can turn on per channel.

The same agent can also answer in Microsoft Teams, since Claude Agent SDK agents support both Slack and Teams. Agents on the OpenAI Responses runtime have the same Stable GPT tier rows, with exact releases under Other versions. If a Responses agent was saved with the none reasoning effort and now runs on a model that rejects it, such as GPT-6.2 Sol, Runbear sends low instead.

On Claude Agent SDK agents, Runbear-provided access uses Runbear credits, and plans are priced on usage credits rather than seats. See pricing for the current plans.

FAQ

When was GPT-6.2 released?

OpenAI released GPT-6.2 Astra and GPT-6.2 Sol on November 17, 2026, according to its API changelog. There is no GPT-6.2 Terra or Luna yet.

How much does GPT-6.2 Sol cost?

$2 per million input tokens, $0.10 per million cached input tokens, $2.50 per million cache-write tokens (30-minute retention), and $10 per million output tokens on the Standard tier, as of November 2026. That is the same input and output price as GPT-6.1 Sol.

Does Runbear support GPT-6.2 in Slack?

Yes. In a Runbear agent's model settings, the GPT Astra and GPT Sol Stable rows now follow GPT-6.2 Astra and GPT-6.2 Sol. Connect the agent to Slack and your team can @mention it in channels or message it directly. Agents pinned to a specific version, such as GPT-6.1 Sol, stay on that version until someone changes it.

When was GPT-6.1 Sol released?

OpenAI released GPT-6.1 Sol on September 29, 2026, according to its API changelog.

When was GPT-6.1 Terra released?

October 26, 2026. OpenAI describes it as "a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing."

How much does GPT-6.1 Terra cost?

$1 per million input tokens, $0.05 per million cached input tokens, and $5 per million output tokens on the Standard tier, as of October 2026. Prompts over 272K input tokens are billed at 2x input and cache rates and 1.5x output for the whole request.

What is the difference between GPT-6.1 Sol and GPT-6.1 Terra?

OpenAI describes Sol as "near-Astra performance for complex work at a lower cost" and Terra as a fast, efficient model for visual reasoning, precise computer use, and writing. Terra costs half as much per token, has a later knowledge cutoff (June 1 vs April 30, 2026), and supports a none reasoning effort that Sol does not. Both share the same context window, max output, and tool list.

Can I use GPT-6.1 or GPT-6.2 in Slack?

Yes. Build an agent in Runbear, choose GPT Sol or GPT Terra (or GPT Astra) in its model settings, and connect it to a Slack channel. Your team can then @mention it in channels or message it directly. Claude Agent SDK agents can also answer in Microsoft Teams.

Will a Runbear agent move to new GPT releases automatically?

Yes, if you choose a Stable row such as GPT Sol or GPT Terra: it follows the latest available version in that tier, on both Claude Agent SDK and OpenAI Responses agents. An agent set to a specific version stays on it.

Your first teammate is 10 minutes away.

Add Runbear to Slack, hire an agent in chat, and watch it work. Free to start, no credit card.

Want a walkthrough first? Book 20 minutes with our CEO