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.
GPT-5.6 Sol is available on MiniRouter as . The model page has current pricing, provider routes and API setup.
About the model
- 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 linked publisher sources 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 from the publisher’s announcement, grouped by unit.
| 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 evaluations of the first-party API.
GPT-5.6 Sol (max) ranks #6 of 462 model families on their Intelligence Index. Their headline uses the highest-scoring effort setting; every listed setting is below.
- Intelligence Index
- 47.0
- 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
- 74
- Median tokens per second
- First answer token
- 71s
- Median seconds, including reasoning
| Setting | Intelligence Index | Coding Index | Blended price | Output speed | First answer token |
|---|---|---|---|---|---|
| GPT-5.6 Sol (max) ↗ | 47.0 | 77.4 | $8 | 74 | 71s |
| GPT-5.6 Sol (xhigh) ↗ | 44.0 | 78.3 | $8 | 71 | 21s |
| GPT-5.6 Sol (high) ↗ | 42.3 | 77.2 | $8 | 66 | 7.8s |
| GPT-5.6 Sol (medium) ↗ | 39.2 | 76.3 | $8 | 61 | 5.4s |
| GPT-5.6 Sol (low) ↗ | 33.5 | 69.7 | $8 | 66 | 2.4s |
| GPT-5.6 Sol (non-reasoning) ↗ | 28.3 | 65.1 | $8 | 62 | 1.1s |
Source: Artificial Analysis ↗, read Sep 21, 2026. Measured on the model's first-party API, not a MiniRouter route.
Keep exploring
Compare published results in the model rankings and coding benchmarks, or read more model releases.
For MiniRouter product updates, visit the changelog.
Sources
- Read at OpenAI ↗
OpenAI GPT-5.6 announcement
Published Jul 9, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 21, 2026
Editorial reference revised 2026-10-17. Catalog status comes from the generated routing snapshot.