Gemini 2.5 Pro vs GPT-5: pricing & cost comparison
Both models charge $1.25 per million input tokens. Both charge $10 per million output tokens.
Side by side
| Gemini 2.5 Pro | GPT-5 | |
|---|---|---|
| Input / 1M tokens | $1.25 | $1.25 |
| Output / 1M tokens | $10 | $10 |
| Context window | 1,000,000 | 400,000 |
| Token-count accuracy | ±3% | exact |
| Cost — 10,000 input + 2,000 output tokens | $0.0325 | $0.0325 |
What a real request costs
Take a representative turn — 10,000 input + 2,000 output tokens. Gemini 2.5 Pro comes to $0.0325, GPT-5 to $0.0325. They're identical on this workload, so pick on quality, context window, or tokenizer accuracy rather than price. Paste your prompt into the calculator to confirm against your real text.
Which should you pick?
These are different vendors, so a switch means a different API and a slightly different tokenizer — budget a small calibration buffer. GPT-5 give exact counts; the others land within a few percent. See the full breakdown on the dedicated pages for Gemini 2.5 Pro and GPT-5.
FAQ
- Is Gemini 2.5 Pro or GPT-5 cheaper?
- Gemini 2.5 Pro and GPT-5 cost the same on this workload ($1.25/$10 per 1M tokens).
- Which has the larger context window?
- Gemini 2.5 Pro, at 1,000,000 tokens versus 400,000.
- How accurate are these token counts?
- Gemini 2.5 Pro: Approximated with o200k_base; drift typically ~3% on English and code. GPT-5: Exact tokenization via the canonical OpenAI vocab (o200k_base). The dollar math itself is exact once the token count is known.