Skip to main content

GPT-6 Luna vs Gemini 3.8 Flash: API pricing compared

GPT-6 Luna is the cheaper of the two: ₹9.75 per 1M input tokens and ₹48.77 per 1M output tokens, against ₹73.15 and ₹366 for Gemini 3.8 Flash. On a workload with three input tokens for every output token, Gemini 3.8 Flash costs 7.5× as much.

GPT-6 Luna accepts more in one request: 10,50,000 tokens of context against 10,48,576 for Gemini 3.8 Flash.

Prices are in rupees per 1M tokens, read from the live catalog. Both models are available on one AICredits key.

GPT-6 Luna vs Gemini 3.8 Flash API pricing and capabilities
FeatureGPT-6 LunaGemini 3.8 Flash
ProviderOpenAIGoogle
Input price (per 1M tokens)₹9.75₹73.15
Output price (per 1M tokens)₹48.77₹365.75
Context window1.1M1.0M
Cached input price (per 1M tokens)₹0.98₹7.32
Vision supportYesYes
Supported APIsChat API, Messages API, Responses APIChat API, Messages API, Responses API
Free tier——
Input price (USD per 1M)$0.10$0.75
Output price (USD per 1M)$0.50$3.75

Rupee prices follow the live USD/INR rate. Green marks the lower price or the larger limit for that row; it says nothing about answer quality, which depends on your task.

What typical requests cost

Cost of typical requests on GPT-6 Luna and Gemini 3.8 Flash
RequestTokens in / outGPT-6 LunaGemini 3.8 Flash
Short chat replya question with a brief answer500 / 300₹0.02₹0.15
Document summaryabout 15 pages in, one page out10,000 / 800₹0.14₹1.02
Coding agent stepfiles and tool results in, a patch out40,000 / 2,000₹0.49₹3.66

Worked out from the prices above, without prompt caching. Enter your own request sizes in the LLM cost calculator.

How to choose between them

Price and limits are on this page; quality on your own task is not something a table can tell you. Both models take the same request on the same key, so the quickest test is to send a sample of your real prompts to each and compare the answers and the cost in your usage log. Changing model is a one-word change in the request.

Use GPT-6 Luna and Gemini 3.8 Flash via one API key

AICredits gives you a single OpenAI-compatible endpoint for both models. Top up in INR via UPI, no international card needed.