← Back to Calculator

GPT-5.6 Luna vs Gemini 3.5 Flash

Detailed comparison of API pricing, technical specifications, and benchmark scores. Updated 2026-06-29.

Cost at a Glance

GPT-5.6 Luna is 4× more expensive than Gemini 3.5 Flash — switching could save 75% on your monthly API bill.

At 5M input + 2M output tokens per month:

GPT-5.6 Luna$17.00/movsGemini 3.5 Flash$4.25/mo

Choosing Gemini 3.5 Flash could save you $12.75/mo

Price Comparison (per 1M tokens)

Input (per 1M tokens)
$1.00vs$0.25
Output (per 1M tokens)
$6.00vs$1.50
Cache Write (per 1M tokens)
$1.25vs
Cache Read (per 1M tokens)
$0.10vs$0.03
Batch Input (per 1M tokens)
$0.50vs
Batch Output (per 1M tokens)
$3.00vs

Prices are per 1 million tokens. Actual costs depend on your monthly token volume. Use the calculator →

Specifications

Context Window
1Mvs1M
Max Output Tokens
64Kvs64K
Knowledge Cutoff
2026-04vs2026-04
Modalities
TextvsText, Image
Prompt Caching
YesvsYes
Batch API
YesvsNo
Thinking / Reasoning
NovsNo

Benchmark Scores

SWE-bench Verified
62.5vs65.0
MMLU-Pro
79.0vs80.0
HumanEval
89.5vs90.0

Benchmark scores from official provider reports. Higher is better. Missing scores indicate the provider has not published that benchmark yet.

Use Cases

GPT-5.6 Luna

fastcheapgeneral

Gemini 3.5 Flash

fastcheapmultimodal

About the Providers

GPT-5.6 Luna is developed by OpenAI. Gemini 3.5 Flash is developed by Google. This is a cross-provider comparison between OpenAI and Google models. For the most up-to-date pricing, always check the official API documentation from each provider.

Compare More AI Models