GPT-6 Luna vs Gemini 2.5 Flash: API cost
Standard, cached and batch API prices for GPT-6 Luna (OpenAI) and Gemini 2.5 Flash (Google), and what each costs for your usage.
GPT-6 Luna is cheaper than Gemini 2.5 Flash at standard rates, with 3× cheaper input and 5× cheaper output.
- Input $3.00
- Cached input $0.3
- Output $4.50
- Input $9.00
- Cached input $0.9
- Output $22.50
Show as a table
| Output tokens | GPT-6 Luna | Gemini 2.5 Flash |
|---|---|---|
| 0 | $0.1 | $0.3 |
| 250 | $0.23 | $0.93 |
| 500 | $0.35 | $1.55 |
| 750 | $0.47 | $2.18 |
| 1,000 | $0.6 | $2.80 |
| Token type | GPT-6 Luna | Gemini 2.5 Flash | |
|---|---|---|---|
| Input | $0.10 | $0.30 | GPT-6 Luna is 3× cheaper |
| Cached input | $0.01 | $0.03 | GPT-6 Luna is 3× cheaper |
| Output | $0.50 | $2.50 | GPT-6 Luna is 5× cheaper |
| Batch input | $0.05 | $0.15 | GPT-6 Luna is 3× cheaper |
| Batch cached input | $0.005 | $0.03 | GPT-6 Luna is 6× cheaper |
| Batch output | $0.25 | $1.25 | GPT-6 Luna is 5× cheaper |
GPT-6 Luna: Long prompts are billed at higher long-context rates.
Gemini 2.5 Flash: Audio input costs more.
| Workload | GPT-6 Luna | Gemini 2.5 Flash |
|---|---|---|
Support chatbot 2,000 in / 300 out tokens,
1,000 requests a day, 50% cached | $7.80 | $32.40 |
Document summaries 10,000 in / 800 out tokens,
200 requests a day | $8.40 | $30.00 |
Tagging / classifying 400 in / 20 out tokens,
20,000 requests a day | $30.00 | $102.00 |
More comparisons
- GPT-6 Sol vs GPT-6 Luna
- GPT-6 Luna vs Claude Haiku 4.5
- GPT-6 Luna vs Gemini 3.5 Flash-Lite
- GPT-6 Luna vs Gemini 3.1 Flash-Lite
- GPT-6 Luna vs Gemini 2.5 Flash-Lite
- Claude Haiku 4.5 vs Gemini 2.5 Flash
- Gemini 2.5 Pro vs Gemini 2.5 Flash
- Gemini 2.5 Flash vs Gemini 2.5 Flash-Lite
Or see GPT-6 Luna pricing, Gemini 2.5 Flash pricing, or compare any two models.
FAQ
Frequently asked questions
Is GPT-6 Luna cheaper than Gemini 2.5 Flash?
GPT-6 Luna is cheaper than Gemini 2.5 Flash at standard rates, with 3× cheaper input and 5× cheaper output. Based on standard API rates last checked on 30 Sept 2026.
How much do GPT-6 Luna and Gemini 2.5 Flash cost per million tokens?
GPT-6 Luna: $0.10 per million input tokens and $0.50 per million output tokens. Gemini 2.5 Flash: $0.30 input and $2.50 output. These are standard rates in USD, before tax, from each provider’s own pricing page.
Which is cheaper with the Batch API?
GPT-6 Luna’s batch rates are $0.05 input and $0.25 output per million tokens (50% off); Gemini 2.5 Flash’s batch rates are $0.15 input and $1.25 output per million tokens (50% off).
Does prompt caching change the comparison?
GPT-6 Luna charges $0.01 per million cached input tokens, against $0.10 for normal input; Gemini 2.5 Flash charges $0.03 per million cached input tokens, against $0.30 for normal input. Cache write and storage charges are extra and aren’t included here.