GPT-6.1 Sol
Unavailable in this round
OpenAI
GPT-6.1 Sol’s main change is stronger coding compared with GPT-6 Sol. In OpenAI’s DeepSWE 1.1 evaluation, it matches GPT-6 Astra while standard input and output token prices are one-fifth of Astra’s. It beats GPT-6 Sol’s best score by 6.4 percentage points at a lower reasoning effort.
Computer use improves too. On OSWorld 2.0’s offline set, OpenAI reports a seven-percentage-point gain over its predecessor at maximum reasoning effort. In that configuration, it trails Astra by 2.1 percentage points.
| Specification | Value and source |
|---|---|
| Weights | ProprietarySource |
| Access | APISource |
| Context window | 1,050,000 tokensSource |
| Knowledge cutoff | April 30, 2026Source |
| Notes | OpenAI describes GPT-6.1 Sol as an upgrade to GPT-6 Sol for complex coding, computer-use and professional tasks. It is available through the API, ChatGPT Work and Codex, but not in ChatGPT Chat at launch.Source |
| API model ID | gpt-6.1-solSource |
| Maximum output | 128,000 tokensSource |
| Input | Text, ImageSource |
| Output | TextSource |
| Reasoning mode | low, medium, high, xhigh, max (default: medium)Source |
| Tool calling | YesSource |
| Structured output | YesSource |
| API interfaces | Responses API, Chat Completions APISource |
One SVG prompt and fixed output settings. Captures are shown only with 0 reported reasoning tokens or documented lack of reasoning controls. Identical test conditions do not make the models' internal compute identical.
Unavailable in this round
A community classic for free-form SVG drawing.
GPT-6.1 Sol

Reasoning (requested): high
Visually reviewed. This individual test does not establish overall model quality.
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)84 / 100
OpenAI calls GPT-6.1 Sol an upgrade to GPT-6 Sol and compares the two directly on coding, computer-use, professional-work and factuality evaluations.
Introducing GPT-6.1 Sol (2026-09-29)| Type | Evidence and data date |
|---|---|
| Price | Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. |
| Input | Documented modalities. Retrieved September 29, 2026. |
| Output | Documented modalities. Retrieved September 29, 2026. |
| Research status | Research date September 29, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | parameters-billions Original wording OpenAI does not publish parameter counts. |
| Unresolved | benchmarks Original wording The launch announcement describes comparative evaluations, but no exact score was transcribed into this record without an unambiguous numeric source table and configuration. |
| Additional source | Model metadata (retrieved September 29, 2026) · Introducing GPT-6.1 Sol · Editorial description reviewed October 4, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |