GPT-6 Sol
ModelActiveby OpenAI · family “gpt-sol”
GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding professional... (description from the OpenRouter listing)
in: filein: imagein: textout: textReasoningTool useStructured output
Epoch Capabilities Index
Not scored by Epoch AI
Released
22 Sep 2026
Context window
1.05M tokens
Max output
128K tokens
Input $ / 1M tokens
$2.00
Output $ / 1M tokens
$10.0
Cached input $ / 1M
$0.20
Each benchmark shown separately with its own source
Benchmark results (8)
| Benchmark | Domain | Score | vs best recorded | Setting | Run | Source |
|---|---|---|---|---|---|---|
| Furniture Assembly | multimodal | 58.3% ±6.4 | 70% | max | 23 Sep 2026 | Epoch ↗ |
| LMCA | agents | 59.1% | 87% | max | — | External ↗ |
| DTBench | reasoning | 97.3% | 98% | max | — | External ↗ |
| EBR-bench | reasoning | 53.3% ±4.6 | 70% | max | 22 Sep 2026 | Epoch ↗ |
| FrontierCode | coding | 49.3% | 92% | max | — | External ↗ |
| APEX-Agents | agents | 54.3% | 72% | max | — | External ↗ |
| ARC-AGI-2 | reasoning | 89.6% | 94% | max | — | External ↗ |
| ARC-AGI | reasoning | 95.5% | 97% | max | — | External ↗ |
Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.
API list price over time
Price history
$ per 1M tokens
Unchanged since first recorded on 27 Sep 2026 (OpenRouter listing); re-read on every data refresh, most recently 10h ago. Steps show when the price changed.
Events
- BenchmarkEpoch AI evaluates GPT-6 SolEpoch AI Benchmarking Hub
- Model launchMajorOpenAI releases GPT-6 SolOpenRouter models API
- BenchmarkEpoch AI evaluates GPT-6 SolEpoch AI Benchmarking Hub