Gemini 3.5 Flash vs GPT-5.6 Luna

Price, context window & benchmark comparison

G

Gemini 3.5 Flash

Google
$1.50 / $9.00
Input / Output · per 1M tokens
VS
O

GPT-5.6 Luna

OpenAI
$0.20 / $1.20
Input / Output · per 1M tokens
Compare different models
G
O
Verdict: GPT-5.6 Luna is 7.5× cheaper than Gemini 3.5 Flash on a typical 3:1 input/output mix. GPT-5.6 Luna scores higher on the Artificial Analysis Intelligence Index (37.3 vs 32.6). GPT-5.6 Luna has the larger context window (1.1M vs 1M).
Gemini 3.5 FlashGPT-5.6 Luna
Input price / 1M$1.50$0.20
Output price / 1M$9.00$1.20
Blended price (3:1)$3.38$0.45
Cached input / 1M$0.15$0.02
Context window1M1.1M
Max output66K128K
Intelligence index32.637.3
Coding index70.171.4
Providers7
Best provider uptime (30m)100.0%
Vision inputYesYes
ReasoningYesYes
Tool callingYesYes
Released2026-05-192026-07-09
Retirement

Cost calculator

FAQ

Which is cheaper, Gemini 3.5 Flash or GPT-5.6 Luna?

GPT-5.6 Luna is 7.5× cheaper than Gemini 3.5 Flash on a typical 3:1 input/output mix.

Gemini 3.5 Flash vs GPT-5.6 Luna: which has a bigger context window?

Gemini 3.5 Flash: 1,048,576 tokens. GPT-5.6 Luna: 1,050,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Gemini 3.5 Flash ≈ $7,500, GPT-5.6 Luna ≈ $1,000.

More comparisons