Pyyan / Compare / o3 / o4-mini vs GPT-6.1 Sol
o3 / o4-mini vs GPT-6.1 Sol
2 of 5Language Models · verified 1 Oct 2026
o3 / o4-miniOpenAIretiredGPT-6.1 SolOpenAIcurrent| Specification | o3 / o4-mini | GPT-6.1 Sol |
|---|---|---|
| Summary | The o-series reasoning line, retired Feb 2026. | Astra's score on DeepSWE, at a fifth of Astra's cost. |
| Context | — | 1.05M |
| Input ($/Mtok) | — | $2 |
| Output ($/Mtok) | — | $10 |
| Licence | Proprietary | Proprietary |
| Max output | — | 128K |
| Parameters | — | Not published |
| Released | — | 29 Sep 2026 |
| Model ID | — | gpt-6.1-sol |
| Category | Language Models | Language Models |
| Official | OpenAI ↗ | OpenAI ↗ |
Highlighted rows are where these differ.
o3 / o4-mini
- Reasoning is now an effort setting on GPT-5.x, not a separate model
Best for nothing — migrate.
GPT-6.1 Sol
- Matches GPT-6 Astra on DeepSWE v1.1 at roughly a fifth of the cost
- $5.47 per Terminal-Bench Science task against $23.80 for Astra
- Above 272K tokens a prompt bills at 2x input and 1.5x output for the whole request
Best for coding and agent work at volume.