GPT-6.1 Sol

Where can you use GPT-6.1 Sol?

The API model ID is gpt-6.1-sol. OpenAI lists it for the API and eligible Plus, Pro, Business, Enterprise, and Edu access in ChatGPT Work and Codex. That list does not mean the model is selectable in ordinary Chat; the launch says Chat support is coming later. Check your own account, workspace settings, and region before switching.

Context, tools, and reasoning limits

The model documentation lists text and image input, text output, 1,050,000 context tokens, 128,000 maximum output tokens, and a knowledge cutoff of April 30, 2026. Reasoning effort runs from low to max, with medium documented as default; none and minimal are not supported. Use the Responses API for tool calling. Chat Completions does not provide its tool-calling contract.

What does the API cost?

Standard API prices per million tokens are $2 input, $0.10 cached input, $2.50 cache write, and $10 output. Above 272,000 input tokens, OpenAI prices the entire request at $4 input, $0.20 cached input, $5 cache write, and $15 output. Fast mode doubles applicable rates, while Batch and Flex have separate discounts. Check residency and mode availability before assuming the same route works in every region.

How does it compare with GPT-6 Sol?

GPT-6 Sol remains the direct predecessor and the current standard input/output list-rate comparison. GPT-6.1 Sol halves the listed cached-input rate and has a different reasoning-effort range. OpenAI describes performance close to Astra at a fraction of Astra's standard token price, but that vendor comparison does not predict quality or cost on every repository or agent task.

• GPT-6 Sol

  Compare the predecessor's access and cached-input price.

Ultrafast is now an API service tier

The October 8 API changelog adds Ultrafast for gpt-6.1-sol in the Responses API, available to API users subject to rate limits. Set service_tier to ultrafast on the same model ID; it is not a new model. API Ultrafast rates are six times Standard: $12 input, $0.60 cached input, $15 cache write and $60 output per million tokens at short context, with separate long-context rates. Work/Codex plan eligibility remains distinct: Pro 500 and eligible Enterprise/Edu credit-based access do not imply access for Plus, Pro 100/200 or Business.

October 21 Google Cloud private preview

Google Cloud’s October 21 announcement names GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna in a Model Garden private preview for selected enterprise customers, with Marketplace billing and Google Cloud APIs. This is not general availability and does not change OpenAI’s direct API IDs, prices or account eligibility. GPT-6 Sol is not the Sol version listed in this preview.

• GPT-6.1 Terra

  A separate October 26 model for visual work, computer use and writing.

Subscription context differs from the API

OpenAI documents a default 500K-token context window for GPT-6.1 Sol in Codex and ChatGPT Work. Subscription usage has no long-context surcharge. The API remains a separate contract with a 1,050,000-token context limit and full-request surcharges above 272K input tokens; do not apply the subscription rule to API billing.

Useful first jobs

• Coding tasks with tests and human review.
• Tool-using agents on the Responses API.
• Long-context analysis with measured cache behavior.