GPT-5.6 Sol
OpenAI's flagship GPT-5.6 tier for long-running coding, research, and professional workflows, with a revised API list price and publisher-reported coding benchmarks.
Routable on MiniRouter
Use openai/gpt-5.6-sol via the API →- Current price
- $5 / $30
- Per 1M input / output tokens after OpenAI's Aug 21 price update
- Cached input
- 90% discount
- Cache writes bill at 1.25× uncached input; reads receive the stated discount
- Reasoning
- up to max
- OpenAI also describes ultra as a multi-agent execution mode
- Family
- Sol / Terra / Luna
- Sol is the flagship tier in the three-model GPT-5.6 family
Publisher pricing
Pricing below comes from the release announcement and does not represent a MiniRouter route or price.
| Phase | Input / 1M | Output / 1M | Blended / 1M | Effective | Source |
|---|---|---|---|---|---|
| Current list price | $5.00 | $30.00 | $11.25 | Aug 21, 2026 – open-ended | OpenAI ↗ |
Publisher-reported benchmarks
Results are grouped by unit. Percentage, Elo, and task-count results never share a scale.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| SWE-Bench Pro | 64.6% | OpenAI | Jul 9, 2026 | Announcement ↗ |
| DeepSWE v1.1 | 72.7% | OpenAI | Jul 9, 2026 | Announcement ↗ |
| Terminal-Bench 2.1 | 88.8% | OpenAI | Jul 9, 2026 | Announcement ↗ |
| GPQA Diamond | 94.6% | OpenAI | Jul 9, 2026 | Announcement ↗ |
- — OpenAI updated the GPT-5.6 announcement on August 21, 2026 to reflect a lower Sol API price.
- — OpenAI reports the benchmark figures; MiniRouter has not reproduced them.
Independent measurements
Artificial Analysis runs its own evaluations and timing against each model's first-party API. These are the only numbers on this page not reported by the publisher.
GPT-5.6 Sol (max) ranks #4 of 448 model families on their Intelligence Index. Their headline uses the highest-scoring effort setting; every listed setting is below.
- Intelligence Index
- 60.9
- Composite of their evaluations
- Coding Index
- 77.4
- Coding evaluations only
- Blended price
- $8
- USD per 1M tokens, 3:1 input to output, first-party list
- Output speed
- 76
- Median tokens per second
- First answer token
- 86s
- Median seconds, including reasoning
| Setting | Intelligence Index | Coding Index | Blended price | Output speed | First answer token |
|---|---|---|---|---|---|
| GPT-5.6 Sol (max) ↗ | 60.9 | 77.4 | $8 | 76 | 86s |
| GPT-5.6 Sol (xhigh) ↗ | 59.0 | 78.3 | $8 | 75 | 24s |
| GPT-5.6 Sol (high) ↗ | 57.3 | 77.2 | $8 | 76 | 9.0s |
| GPT-5.6 Sol (medium) ↗ | 55.6 | 76.3 | $8 | 76 | 7.2s |
| GPT-5.6 Sol (low) ↗ | 50.7 | 69.7 | $8 | 71 | 2.1s |
| GPT-5.6 Sol (non-reasoning) ↗ | 41.9 | 65.1 | $8 | 67 | 1.1s |
Source: Artificial Analysis ↗, read Sep 2, 2026. Measured on the model's first-party API, not a MiniRouter route.
What is not independently confirmed
- Every figure on this page is self-reported by the cited publisher. MiniRouter did not run these benchmarks.
- Benchmark harnesses are not standardised. Results sharing a name across vendors have not been confirmed to use identical runs.
- Publisher pricing can change, and introductory phases have stated end dates.
- GPT-5.6 Sol is routable through MiniRouter today; live pricing on its model page is authoritative over the publisher figures here.
Related coverage
Other release dossiers and the current MiniRouter catalog.
Sources
- Read at OpenAI ↗
OpenAI GPT-5.6 announcement
Published Jul 9, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 2, 2026
Editorial reference revised 2026-09-02. Catalog status comes from the generated routing snapshot.