Verified against the provider's official pricing page on Oct 9, 2026. Official pricing page Long-context and separately billed token prices, where shown, are list prices compiled by models.dev (checked Oct 10, 2026, 09:00 UTC).
Monthly cost by workload
Workload
Gemini 3.8 Flash
GPT-6 Luna
Chatbot1,000 in / 500 out tokens, 10,000 requests a day
$787.50/mo
$105.00/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day
$1,181/mo
$157.50/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input
$540.00/mo
$72.00/mo
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Context and capabilities
Gemini 3.8 Flash
GPT-6 Luna
Context
1,048,576 tokens
1,050,000 tokens
Max output
65,536 tokens
128,000 tokens
Input
text, image, video, audio, pdf
text, image, pdf
Tool calling
Yes
Yes
Reasoning
Yes
Yes
Structured outputs
Yes
Yes
Questions
What is the price difference between Gemini 3.8 Flash and GPT-6 Luna?
Gemini 3.8 Flash: $0.75 per 1M input tokens and $3.75 per 1M output tokens. GPT-6 Luna: $0.10 per 1M input tokens and $0.50 per 1M output tokens. For the Chatbot workload (1,000 in / 500 out tokens, 10,000 requests a day), that is about $787.50 per month for Gemini 3.8 Flash and $105.00 for GPT-6 Luna.
Which has the longer context window, Gemini 3.8 Flash or GPT-6 Luna?
GPT-6 Luna has the longer context window: up to 1,050,000 tokens, compared with 1,048,576 for Gemini 3.8 Flash.
Do Gemini 3.8 Flash and GPT-6 Luna have prompt caching and batch prices?
Gemini 3.8 Flash: cached input $0.075 per 1M tokens; batch $0.375 per 1M input tokens and $1.875 per 1M output tokens. GPT-6 Luna: cached input $0.01 per 1M tokens; batch $0.05 per 1M input tokens and $0.25 per 1M output tokens.