With ChatGPT sign-in, OpenAI recommends GPT-6.1 Sol for complex coding and agentic work and GPT-6 Luna for focused, repeatable tasks. GPT-5.5 retires from Codex on October 14, 2026 (it stays on the API), and GPT-5.4, GPT-5.4 Mini and GPT-5.3-Codex are already gone for ChatGPT sign-in. The GPT-5.6 tiers below remain selectable during the GPT-6 rollout.
Run any of these models in your agent
Or let the router send each step to the cheapest model that can do it, on providers we vet for price, uptime and speed. Plans from $19 a month.
OpenAI's recommended Codex model for complex coding: ties GPT-6 Astra at 58.2% on Terminal-Bench 4.0 at a fifth of the API price.
OpenAI's most capable model, for the hardest work. It spends a ChatGPT plan's Codex allowance much faster than Sol or Luna.
The efficient option for focused, repeatable tasks, and OpenAI's suggestion on the Free and Go plans.
The strongest GPT-5.6 tier, for hard coding and research when GPT-6.1 Sol isn't available to your account yet.
OpenAI's balance of speed, capability and cost for everyday work such as routine code changes.
A fast, economical option for focused or repetitive steps: extraction, categorizing and short edits.
A typical request sends 99,534 input tokens, 87% of them read from cache, and a median session runs 16 requests. Measured on pooled coding-agent requests through our gateway (79,301 requests from 75 users; Codex alone has fewer than 50 users, so its traffic is pooled), Sep 13 to Oct 12, 2026, priced at each vendor's list rates.
| Model | 100 requests | Median session | Month of regular use |
|---|---|---|---|
| GPT-6.1 Sol | $6.74 | $0.74 | $90.04 |
| GPT-6 Astra | $41.25 | $4.49 | $583 |
| GPT-6 Luna | $0.41 | $0.045 | $5.83 |
| GPT-5.6 Sol | $16.50 | $1.80 | $233 |
| GPT-5.6 Terra | $8.40 | $0.92 | $118 |
| GPT-5.6 Luna | $0.84 | $0.092 | $11.83 |
Month of regular use = the median user active on 5 or more days (1,478 requests in 30 days). Methodology · All models ranked by cost per request
The highest-rated model whose list-price cost for a month of regular use (1,478 requests) stays under each budget. Heavier months cost proportionally more.
| Monthly budget | Best model that fits | Est. month |
|---|---|---|
| Under $19 | GPT-6 Luna | $5.83 |
| Under $49 | GPT-6 Luna | $5.83 |
| Under $99 | GPT-6.1 Sol | $90.04 |
"Highest-rated" uses our editorial quality and agentic scores; candidates are current models that Codex runs with a checked vendor price.
The agent matters as much as the model. Compare AI agents →
Every model on this page runs on Standard Compute
