Gemini 2.5 Pro vs GPT-5.6 Luna — Side-by-side pricing
Side-by-side API pricing and tokenizer details for Gemini 2.5 Pro (Google) and GPT-5.6 Luna (OpenAI).
Side-by-side pricing
| Feature | Gemini 2.5 Pro | GPT-5.6 Luna |
|---|---|---|
| Provider | OpenAI | |
| Input (per 1M tokens) | $1.25 | $1.00 |
| Output (per 1M tokens) | $10.00 | $6.00 |
| Long-context pricing | Over 200K tokens: $2.50 in / $15.00 out | Over 272K tokens: $2.00 in / $9.00 out |
| Context caching | No | Yes — 90% off cached tokens |
| Batch API discount | Not available | 50% off |
| Context window | 1M tokens | 1.1M tokens |
| Tokenizer | Gemini tokenizer | o200k_base (tiktoken) |
Real-world cost example
1,000 API requests per month, each with 500 input tokens and 200 output tokens (500K input + 200K output total).
Gemini 2.5 Pro
$2.6250
Input: $0.6250 +Output: $2.0000
GPT-5.6 Luna
$1.7000
Input: $0.5000 +Output: $1.2000
GPT-5.6 Luna is 35% cheaper for this workload — saving $0.9250 per month at this volume.
Frequently asked questions
No, GPT-5.6 Luna is cheaper for the typical workload above. At $1.00/1M input and $6.00/1M output tokens, it costs $1.7000 versus $2.6250 for Gemini 2.5 Pro — a 35% difference. Note that both models switch to long-context pricing — Gemini 2.5 Pro above 200K prompt tokens and GPT-5.6 Luna above 272K — so for very long prompts this gap does not scale linearly.
Gemini 2.5 Pro supports a 1M token context window. GPT-5.6 Luna supports a 1.1M token context window. A larger context window lets you include more text — documents, conversation history, or code — in a single API call.
Gemini 2.5 Pro does not support context caching. It does not offer a batch API discount. GPT-5.6 Luna supports context caching (90% off repeated tokens). It offers a 50% Batch API discount.
No, they use different tokenizers. Gemini 2.5 Pro uses the Gemini tokenizer, while GPT-5.6 Luna uses o200k_base (tiktoken). Different tokenizers split text differently, so the same prompt will produce different token counts on each model — the effective cost difference may be larger or smaller than the per-token price difference alone suggests.
Gemini 2.5 Pro (Google): $1.25 input / $10 output per 1M tokens. GPT-5.6 Luna (OpenAI): $1 input / $6 output per 1M tokens. Rates shown before caching or batch discounts.
For an 80% output / 20% input workload — typical for code generation or long-form writing — Gemini 2.5 Pro costs $8.2500 per 1M total tokens and GPT-5.6 Luna costs $5.0000. GPT-5.6 Luna is 39% cheaper for this pattern. For your exact ratio, paste a real prompt into the calculator above.
Gemini 2.5 Pro has a 1M-token context window — approximately 750K words or ~3K pages of standard text. GPT-5.6 Luna has a 1.1M-token context window — approximately 788K words or ~3K pages. (Estimates assume ~0.75 words per token.)
Calculate costs for your actual prompt
Paste your prompt into the calculator and get exact token counts using each model's real tokenizer — all in your browser.
Open calculator