GPT-6 Luna vs Gemini 3.8 Flash: API price, context and cost per task
The budget tiers of OpenAI and Google: GPT-6 Luna, the fast, cost-efficient model of the GPT-6 series, and Gemini 3.8 Flash, Google's most capable Flash model.
On output, GPT-6 Luna is 8.3x cheaper ($0.5 vs $4.13 per million tokens). On input, GPT-6 Luna is 8.2x cheaper ($0.1 vs $0.825 per million tokens). GPT-6 Luna reads more per request: 1,050,000 tokens against 1,048,576.
Data updated 2026-11-11 - source: public OpenRouter model list, refreshed daily. Prices in USD, excluding VAT.
Specs and prices side by side
| GPT-6 Luna | Gemini 3.8 Flash | |
|---|---|---|
| Vendor | OpenAI | |
| Input, per 1M tokens | $0.1 | $0.825 |
| Output, per 1M tokens | $0.5 | $4.13 |
| Cached input, per 1M | $0.01 | $0.0825 |
| Batch (input / output) | $0.05 / $0.25 | $0.375 / $1.88 |
| Context window | 1,050,000 | 1,048,576 |
| Max output | 128,000 | 65,536 |
| Input types | text, images, files | text, images, files, audio, video |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| On OpenRouter since | 22 Sep 2026 | 2 Sep 2026 |
Highlighted: the cheaper price or the larger limit. "Not published" means the figure is not in the public model listing yet.
What a month of work costs
Four typical workloads at today's list prices. Reasoning models also bill their thinking as output tokens, so treat output-heavy numbers as a floor.
| Workload | GPT-6 Luna | Gemini 3.8 Flash | Difference |
|---|---|---|---|
| Support chatbot10,000 conversations a month, about 1,500 input and 400 output tokens each | $3.50 | $28.88 | GPT-6 Luna 8.3x cheaper |
| Coding agent300 tasks a month, about 80,000 input tokens (code context re-read across steps) and 8,000 output tokens each | $3.60 | $29.70 | GPT-6 Luna 8.2x cheaper |
| Coding agent with caching70% of input served from the prompt cache | $2.09 | $17.23 | |
| Long-document analysis1,000 documents a month, about 50,000 tokens in and a 1,500-token summary out | $5.75 | $47.44 | GPT-6 Luna 8.3x cheaper |
| Content drafting600 articles a month, about 3,000 tokens of brief in and 2,500 tokens of draft out | $0.93 | $7.67 | GPT-6 Luna 8.2x cheaper |
Price stability over the last 30 days
- GPT-6 Luna: no change in the last 30 days.
- Gemini 3.8 Flash: 1 price change since 12 Oct 2026. Input ranged $0.75 - $0.825, output $3.75 - $4.13 per million tokens.
Gemini 3.8 Flash: price log
| Date | Input | Output |
|---|---|---|
| 2026-10-16 | $0.825 | $4.13 |
| 2026-09-08 | $0.75 | $3.75 |
What the vendors and benchmarks say
GPT-6 Luna
"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol."model card on OpenRouter
Gemini 3.8 Flash
"Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning."model card on OpenRouter
Which one to pick
Luna is the cheaper of the two at list prices and has the larger output limit. Gemini 3.8 Flash accepts audio and video as well as images and files, which Luna does not. For text and document pipelines, Luna; for multimodal input, Flash.
Cheaper models with a similar context window
Models from our comparison set that cost less than both on a blended basis and support tool calling. They are not equivalent in quality - test before switching.
- DeepSeek V4.1 Flash (DeepSeek): $0.051 / $0.567 per million tokens, 1.05M context
Related reading
How we calculate
Prices are the public per-token list rates from OpenRouter's model list, which match the vendors' own API prices for first-party models and show the current routed price for open-weight models served by several hosts. Monthly costs multiply those rates by the token volumes in each workload; caching assumes the stated share of input is billed at the cached-input rate. Benchmarks and claims are quoted from the named sources, mostly the vendors themselves - treat them as a guide and test on your own tasks. See also the AI cost calculator and all tracked model prices.
Frequently asked questions
Which is cheaper, GPT-6 Luna or Gemini 3.8 Flash?
As of 11 Nov 2026, GPT-6 Luna costs $0.1 per million input tokens and $0.5 per million output tokens; Gemini 3.8 Flash costs $0.825 and $4.13. GPT-6 Luna is cheaper in 4 of the 4 monthly workloads we price on this page. The real bill also depends on how many reasoning tokens each model writes.
Which has the larger context window?
GPT-6 Luna reads up to 1,050,000 tokens and can write up to 128,000; Gemini 3.8 Flash reads up to 1,048,576 and writes up to 65,536.
How much does a support chatbot cost on each model?
For 10,000 conversations a month (about 15 million input and 4 million output tokens) you would pay about $3.50 on GPT-6 Luna and $28.88 on Gemini 3.8 Flash at list prices, before any caching or batch discounts.
Do they offer prompt caching or batch discounts?
GPT-6 Luna lists cached input at $0.01 per million and a batch rate of $0.05 / $0.25. Gemini 3.8 Flash lists cached input at $0.0825 per million and a batch rate of $0.375 / $1.88. Caching matters most for agents and chatbots that resend the same context on every turn.
// follow
New tests and price changes, straight to your feed reader
Free RSS, no account and no email needed.
Follow Quantslant →