# gpt-6-sol decision evidence

GPT-6 Sol is OpenAI's closed-weight model for complex coding and agentic work, released on 2026-09-22 as a lower-cost alternative to GPT-6 Astra, with a 1,050,000-token context window (922,000 input), 128,000 output tokens and text and image input. Reviewed tests find it faster and cheaper than Astra and Claude Opus 5.5, using about an eighth of Astra's quota in one test; on quality, one $20-plan comparison scored it highest of three, while in two one-prompt builds Opus 5.5 produced the fuller or preferred result.

Verified: 2026-09-24; snapshot: 2026-09-24.

## Published model card

As the vendor publishes it for the model and its weights; these are not the limits of a hosted endpoint.

- Context window: 1,050,000 tokens (up to 922,000 input)
- Maximum output: 128,000 tokens
- Modalities: Text and image input; text output
- Parameter count: Not disclosed

## Open weights and deployment

Status: Unavailable. OpenAI publishes no GPT-6 Sol weights. The model is served through the OpenAI API (Responses, Chat Completions and Batch) and on Amazon Bedrock in us-east-1.

Open-weight alternatives: [mimo-v2.6-pro](https://dash.chinaapi.ai/models/mimo-v2.6-pro/deploy), [deepseek-flash](https://dash.chinaapi.ai/models/deepseek-flash/deploy)

## Real-task reports

### [Claude Opus 5.5 and GPT-6 Sol on one interactive website prompt](https://x.com/Kappaemme1926/status/2102729710174196022)

By [Kappaemme](https://x.com/Kappaemme1926) (@Kappaemme1926). X user who posted this side-by-side test

Published: 2026-09-23; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: Build an interactive website about imaginary planets from a single prompt
- Method: Same prompt with both models on High; the author reported wall-clock time, how much each result covered and the share of each subscription's usage.
- Finding: GPT-6 Sol took 10 minutes and built three planets, using 1% of the $200 plan's usage; Claude Opus 5.5 took 26 minutes for a fuller, explorable solar system with more detail, using 16% of the $20 plan's usage. The author found the planets surprisingly similar: Sol faster, Opus bigger and more detailed.
- Limitation: One prompt judged by the author; the usage shares are meters of two different subscription plans, not API costs.
- GPT-6 Sol time: 10 min
- Claude Opus 5.5 time: 26 min

### [Four models build the Eiffel Tower in Three.js](https://x.com/Bhavani_00007/status/2102795814355763277)

By [Bhavy](https://x.com/Bhavani_00007) (@Bhavani_00007). X user who ran the same Three.js task on four models and reported cost and time

Published: 2026-09-23; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: Build the Eiffel Tower in Three.js
- Method: Same task on Claude Opus 5.5, GPT-6 Astra, GPT-6 Sol and Kimi K3; the author reported cost and time for each and compared the results by eye.
- Finding: GPT-6 Sol was the cheapest and fastest of the four at $3.90 and 5 minutes, but the author found its result a bit disappointing; they preferred Claude Opus 5.5 ($8.95, 10 minutes) and rated Kimi K3 ($4.04, 6 minutes) strong for the price.
- Limitation: One task judged by eye by the author; the post does not say how the models were run or how the costs were counted.
- GPT-6 Sol: $3.90 · 5 min
- Claude Opus 5.5: $8.95 · 10 min

### [Claude Pro, Codex Plus and SuperGrok on the same work at maximum settings](https://x.com/shownotover/status/2102950408465338855)

By [shownotover](https://x.com/shownotover) (@shownotover). X user comparing $20 AI subscriptions in their first video

Published: 2026-09-24; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: One piece of work run on each $20 subscription; the task itself is shown only in the author's video
- Method: Each plan's top model at maximum reasoning (Grok 4.7 at xhigh); the author recorded the share of the weekly limit, tokens, working time and a 1–10 quality score.
- Finding: GPT-6 Sol on Codex Plus used 9% of the weekly limit (29 million tokens) over 69 minutes and scored 7/10, the highest of the three plans, against 5/10 for Opus 5.5 and 6/10 for Grok 4.7; the author still recommends Claude at $20 because it yields far more tokens, and puts Codex Plus at about $330 of API usage a month.
- Limitation: The post does not describe the task, the quality score is the author's own, and the numbers are subscription meters rather than API usage.
- Quality (author): 7/10
- Working time: 69 min
- Tokens: 29M

### [GPT-6 Astra, Sol and Luna on one SVG animation prompt](https://x.com/xueyu1125/status/2102692499710193960)

By [雪瑜](https://x.com/xueyu1125) (@xueyu1125). Programmer and AI-tools builder on X who posted the timings and quota readings

Published: 2026-09-23; retrieved: 2026-09-24; verified: 2026-09-24.

- Task: Generate an SVG animation of a pelican riding a bicycle, shown in H5
- Method: Same prompt on GPT-6 Astra, GPT-6 Sol, GPT-6 Luna and GPT-5.6 Sol; the author recorded time taken and the share of a five-hour subscription quota each used.
- Finding: GPT-6 Sol took 4 min 42 s and used 2% of the five-hour quota, against 6 min 3 s and 16% for GPT-6 Astra; the author puts Sol's quota use at an eighth of Astra's and recommends Sol when quota matters.
- Limitation: One prompt; the quota shares are a subscription meter, not API cost, and the post gives no quality score for Sol.
- Time: 4 min 42 s
- Five-hour quota used: 2%

## Public leaderboard coverage

A board missing from this list has no figure for this model in this snapshot; missing coverage is not a zero.

- Artificial Analysis Intelligence Index — Intelligence Index: 48 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · Output Speed — Median output tokens/s: 104 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · GDPval-AA v2.1 — Agentic Real-World Work Tasks, (Elo-500)/2000 (%): 49 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)
- Artificial Analysis · Terminal-Bench v4.0 — Agentic Coding & Terminal Use (%): 44 (retrieved 2026-09-22) [source](https://artificialanalysis.ai/leaderboards/models)

## Curated comparisons

- [claude-opus-5-5 vs gpt-6-sol](https://dash.chinaapi.ai/models/compare/claude-opus-5-5-vs-gpt-6-sol)
- [gpt-6-astra vs gpt-6-sol](https://dash.chinaapi.ai/models/compare/gpt-6-astra-vs-gpt-6-sol)
- [gpt-6-luna vs gpt-6-sol](https://dash.chinaapi.ai/models/compare/gpt-6-luna-vs-gpt-6-sol)

## Official sources

- [GPT-6 Sol model documentation](https://developers.openai.com/api/docs/models/gpt-6-sol) — OpenAI, retrieved 2026-09-24
- [OpenAI API changelog](https://developers.openai.com/api/docs/changelog) — OpenAI, retrieved 2026-09-24
- [GPT-6 Astra System Card (appendix on GPT-6 Sol and GPT-6 Luna)](https://deploymentsafety.openai.com/gpt-6-astra) — OpenAI, retrieved 2026-09-24