Gemini 3.8 Flash vs GPT-6 Luna: pricing and benchmarks
GPT-6 Luna is 87% cheaper on input tokens ($0.10 vs $0.75 per 1M). GPT-6 Luna is 87% cheaper on output tokens ($0.50 vs $3.75 per 1M). On our document Q&A workload (50,000 questions a month), GPT-6 Luna costs $55.00 a month versus $412.50 for Gemini 3.8 Flash, 87% less. Roughly tied. Gemini 3.8 Flash scores 157.2 and GPT-6 Luna scores 156.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
Which should you choose?
Roughly tied. Gemini 3.8 Flash scores 157.2 and GPT-6 Luna scores 156.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
GPT-6 Luna scores 78.9% on FrontierMath (Tiers 1–3) vs 68.4% for Gemini 3.8 Flash.
GPT-6 Luna costs $0.20 per 1M tokens (3:1 input-to-output mix) vs $1.50 for Gemini 3.8 Flash, 87% less.
GPT-6 Luna delivers statistically similar overall capability for 87% less.
Pricing and specs
| Gemini 3.8 Flash | GPT-6 Luna | |
|---|---|---|
| Provider | OpenAI | |
| API model ID | gemini-3.8-flash | gpt-6-luna |
| Input / 1M tokens | $0.75 | $0.10 |
| Cached input / 1M tokens | $0.075 | $0.01 |
| Output / 1M tokens | $3.75 | $0.50 |
| Long-context rates | — | $0.20 in / $0.75 out on long-context requests |
| Context window | 1.05M tokens | 1.05M tokens |
| Max output | 66K tokens | 128K tokens |
| Batch discount | 50% off | 50% off |
Benchmarks
| Gemini 3.8 Flash | GPT-6 Luna | |
|---|---|---|
| Epoch Capabilities Index | 157.2 | 156.3 |
| GPQA Diamond· Science reasoning | 95.4% | 90.5% |
| FrontierMath (Tiers 1–3)· Advanced math | 68.4% | 78.9% |
| SimpleQA Verified· Factual accuracy | 69.7% | 41.4% |
| ARC-AGI-2· Abstract reasoning | 89.2% | 59.3% |
| DeepSWE· Coding | 73.8% | — |
| APEX-Agents· Agentic work | 64.3% | 44.3% |
Source: Epoch AI, best recorded result per model (CC BY 4.0). A dash means no published score. See all benchmarks
Monthly cost for real workloads
| Workload | Gemini 3.8 Flash | GPT-6 Luna | Difference |
|---|---|---|---|
Support chatbot 100,000 replies a month, ~1,500 input tokens (system prompt + history) and ~400 output tokens each. | $262.50 | $35.00 | GPT-6 Luna 87% cheaper |
Document Q&A (RAG) 50,000 questions a month with ~8,000 tokens of retrieved context and ~600 output tokens each. | $412.50 | $55.00 | GPT-6 Luna 87% cheaper |
Coding agent 10,000 agent steps a month, ~40,000 input tokens each (70% read from the prompt cache) and ~2,000 output tokens. | $186.00 | $24.80 | GPT-6 Luna 87% cheaper |
Cached chatbot The same 100,000-reply support chatbot, but 60% of each prompt (system prompt + conversation history) is served from the prompt cache. | $201.75 | $26.90 | GPT-6 Luna 87% cheaper |
Meeting notes 10,000 meetings a month summarized from ~12,000-token transcripts, ~1,000 output tokens each. | $127.50 | $17.00 | GPT-6 Luna 87% cheaper |
Bulk translation 200,000 short translations a month, ~800 input and ~800 output tokens each. | $720.00 | $96.00 | GPT-6 Luna 87% cheaper |
Content moderation 1,000,000 classifications a month, ~400 input tokens and ~80 output tokens each. | $600.00 | $80.00 | GPT-6 Luna 87% cheaper |
Article drafting 300 long-form articles a month written from a ~4,000-token brief and outline, ~5,000 output tokens each. | $6.52 | $0.87 | GPT-6 Luna 87% cheaper |
Code review bot 30,000 pull-request reviews a month, ~5,000 input tokens each (30% cached repository context) and ~700 output tokens. | $160.88 | $21.45 | GPT-6 Luna 87% cheaper |
Invoice extraction 100,000 documents a month parsed into structured JSON, ~1,200 input and ~250 output tokens each. | $183.75 | $24.50 | GPT-6 Luna 87% cheaper |
Estimates use standard list prices and ignore cache-write surcharges. Different tokenizers can count the same text differently, so test with your own prompts.
Gemini 3.8 Flash vs GPT-6 Luna cost calculator
- $55.00/mo$0.0011 / req
- Gemini 3.8 FlashGoogle$412.50/mo$0.0083 / req
Standard-tier list prices. Long-context rates apply automatically where the provider publishes a threshold. Excludes cache-write surcharges, taxes, batch and volume discounts.
Gemini 3.8 Flash pricing notes
Google’s newest Flash model, with thinking, tool use and a 1M-token context window.
- Introductory price through December 31, 2026. From January 1, 2027: $1.50 input, $0.15 cached, $7.50 output per 1M tokens.
- Output price includes thinking tokens.
- Priority inference costs 1.8x the standard rate.
GPT-6 Luna pricing notes
OpenAI’s most efficient GPT-6 model, for focused, high-volume tasks.
- Cache writes are billed at $0.125 per 1M tokens.
- Fast mode costs 2x the standard rate; Flex costs half.
- Regional (data residency) endpoints add a 10% uplift, and EU data residency is available only with standard processing.
Frequently asked questions
- Is Gemini 3.8 Flash cheaper than GPT-6 Luna?
- GPT-6 Luna is 87% cheaper on input tokens ($0.10 vs $0.75 per 1M). GPT-6 Luna is 87% cheaper on output tokens ($0.50 vs $3.75 per 1M). On our document Q&A workload (50,000 questions a month), GPT-6 Luna costs $55.00 a month versus $412.50 for Gemini 3.8 Flash, 87% less.
- Which is more capable, Gemini 3.8 Flash or GPT-6 Luna?
- Roughly tied. Gemini 3.8 Flash scores 157.2 and GPT-6 Luna scores 156.3 on the Epoch Capabilities Index, and their confidence intervals overlap.
- How much does Gemini 3.8 Flash cost per 1M tokens?
- Gemini 3.8 Flash costs $0.75 per 1M input tokens and $3.75 per 1M output tokens, and $0.075 per 1M cached input tokens on Google’s standard tier.
- How much does GPT-6 Luna cost per 1M tokens?
- GPT-6 Luna costs $0.10 per 1M input tokens and $0.50 per 1M output tokens, and $0.01 per 1M cached input tokens on OpenAI’s standard tier.
- Which has the larger context window, Gemini 3.8 Flash or GPT-6 Luna?
- GPT-6 Luna has the larger context window: 1.05M tokens versus 1.05M for Gemini 3.8 Flash.