Best OpenAI model for code
For code with OpenAI, use GPT-6.1 Sol at high effort.
GPT-6.1 Sol at high effort
High effortreasoning.effort = high
Beats Astra's best on DeepSWE (75.2% vs 74.1%) at a fraction of the cost per task. In ChatGPT it's only in Codex for now. Regular chats don't have it yet.
How it compares
Prices are in US dollars per million tokens, input then output. GPT-6.1 Sol costs $2 / $10.
| Model | Price | Against the pick |
|---|---|---|
| GPT-6 Astra | $10 / $50 | Five times the price per token for, at best, a small edge on some coding tests. |
| GPT-6 SolOlder | $2 / $10 | Replaced by 6.1 Sol at the same price. |
| GPT-6 Luna | $0.10 / $0.50 | Built for cheap, high-volume work and too light for real engineering. |
Setting it in the API
In an API request, set the model and effort like this:
model: "gpt-6.1-sol", reasoning: { effort: "high" }
Maintained by the AI team at Vegan Hacktivists
Prices are per million tokens, input / output. We pick for the best result per dollar, so a pricier model can score higher and still lose out. This pick last changed Oct 9, 2026. Sources: Anthropic docs, OpenAI docs, Gemini docs, Artificial Analysis, Vals AI.Last checked Oct 12, 2026.
Other picks
OpenAI for everyday work, research, agents and automations.
Other labs for code: Claude, Gemini.
Open the interactive picker to switch between labs and tasks.
Want helpputting this to work?
Vegan Hacktivists offers free AI and automation support to animal protection organizations — from a first conversation to a full build.
