GPT-5.6 Luna vs Gemini 3.6 Flash
GPT-5.6 Luna and Gemini 3.6 Flash compared on current per-token rates, context window, and capabilities — both callable through one OpenAI-compatible endpoint with per-request cost traces.
GPT-5.6 Luna vs Gemini 3.6 Flash: rates, context window, and capabilities
| Spec | GPT-5.6 Luna | Gemini 3.6 Flash |
|---|---|---|
| Input / 1M tokens | $0.10 | $0.45 |
| Output / 1M tokens | $0.60 | $2.70 |
| Cached input / 1M tokens | $0.05 | $0.45 |
| Context window | 1.1M | 1.0M |
| Capabilities | Chat, Streaming, Tool calling, Vision | — |
| Detail page | GPT-5.6 Luna | Gemini 3.6 Flash |
What does 1M tokens cost on GPT-5.6 Luna vs Gemini 3.6 Flash?
For a workload of 1M input plus 1M output tokens at current rates: GPT-5.6 Luna comes to $0.70, Gemini 3.6 Flash comes to $3.15 — GPT-5.6 Luna is about 78% cheaper on this mix. Real workloads skew heavily toward input tokens, so weigh the input rate by your own ratio; prompt-cache hits bill at the cached-input rate where supported.
Switch between GPT-5.6 Luna and Gemini 3.6 Flash without changing code
Both models are behind the same OpenAI-compatible endpoint, so an A/B test is a one-string change — same key, same code, and every request traced with tokens, cost, and latency in the dashboard:
curl https://api.router.one/v1/chat/completions \
-H "Authorization: Bearer sk-your-router-one-key" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-5.6-luna", "messages": [{"role": "user", "content": "Hello"}]}'
# Same request, other model — change one string:
# "model": "google/gemini-3.6-flash"FAQ
Is GPT-5.6 Luna cheaper than Gemini 3.6 Flash?
At current posted rates, GPT-5.6 Luna is the cheaper of the two (input $0.10 vs $0.45, output $0.60 vs $2.70 per 1M tokens). Rates change; the /models page is the live source of truth.
Can I switch between GPT-5.6 Luna and Gemini 3.6 Flash without changing code?
Yes. Both are served through the same OpenAI-compatible endpoint, so switching is changing the model string in the request — the key, base URL, and request shape stay identical.
Where do these numbers come from?
Specs and prices on this page render from the live Router One catalog — the same data as the /models page — and refresh with it. Pricing methodology is documented on /pricing-methodology.