OpenAI
GPT 5.6 Luna
openai/gpt-5.6-luna-pro
GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks.
Only tracked on Vercel AI Gateway.
GPT 5.6 Luna usage over time
Vercel AI Gateway share of tokens, by day.
GPT 5.6 Luna holds 4.96% today, up from 0.04% at the start of the visible window.
Rank history
Adoption curve vs the pantheon
GPT 5.6 Luna's share plotted against days since first tracked, overlaid on other current leaders on the same axis. The question every new-model page asks: is this one going to make it?
Citable stat
As of 2026-09-02, GPT 5.6 Luna holds 5.0% of Vercel AI Gateway token share, up 1.61pp over 30 days. Source: Tidelines (Vercel AI Gateway).
Cost per session
Median dollars spent on one GPT 5.6 Luna session, by coding agent and session length.
Token rate sets the price; session length and reasoning set the bill.
| Agent | 1 turn | 2–9 turns | 10–49 turns | 50+ turns |
|---|---|---|---|---|
| Kilo Code | — | $0.032 | $0.253 | $2.23 |
| Hermes Agent | $0.0048 | $0.023 | $0.174 | $1.95 |
| Codex | $0.0044 | $0.026 | $0.167 | $1.45 |
| Claude Code | — | $0.018 | $0.115 | $1.49 |
Where to run it
GPT 5.6 Luna pricing by provider
Per-provider pricing, context, and uptime via OpenRouter. Sorted by output price.
GPT 5.6 Luna is served by 5 tracked endpoints on OpenRouter. The cheapest output price is $0.60 per million tokens from OpenAI · 1050k, and the most expensive is $2.40 from OpenAI · 1050k. The largest context window offered is 1050k tokens. Prices are list rates and refresh daily.
| Provider | Input $/M | Output $/M | Context | Uptime |
|---|---|---|---|---|
| OpenAI · 1050k | $0.10 | $0.60 | 1050k | 100.00% |
| Azure · 1050k | $0.20 | $1.20 | 1050k | — |
| OpenAI · 1050k | $0.20 | $1.20 | 1050k | 99.87% |
| Azure · 1050k | $0.22 | $1.32 | 1050k | — |
| OpenAI · 1050k | $0.40 | $2.40 | 1050k | — |