Pricing comparison
GPT-4o vs Gemini 2.5 Pro
Per-token pricing, full-workload cost ladders, and monthly volume projections. Numbers sourced directly from each provider's rate card.
OpenAI
GPT-4o
- Input
- $2.50 / 1M
- Output
- $10.00 / 1M
- Cached input
- $1.250 / 1M
- Context
- 128K
- Max output
- 16K
Gemini 2.5 Pro
- Input
- $1.25 / 1M
- Output
- $10.00 / 1M
- Cached input
- $0.125 / 1M
- Context
- 2M
- Max output
- -
Cost per request
Four common workload shapes, input tokens and a 1:2 output ratio (a standard chat/completion pattern). Long-context surcharges apply automatically where the provider charges them.
| Scenario | Tokens (in / out) | GPT-4o | Gemini 2.5 Pro | Winner |
|---|---|---|---|---|
| Short prompt | 100 / 200 | $0.0023 | $0.0021 | Gemini 2.5 Pro |
| Typical request | 1,000 / 2,000 | $0.0225 | $0.0213 | Gemini 2.5 Pro |
| Long document | 10,000 / 5,000 | $0.0750 | $0.0625 | Gemini 2.5 Pro |
| Large prompt | 100,000 / 10,000 | $0.3500 | $0.2250 | Gemini 2.5 Pro |
Monthly bill at scale
Projected monthly cost at typical request volume, assuming the "typical request" shape above (1k in, 2k out).
| Traffic | Req / month | GPT-4o | Gemini 2.5 Pro | Delta |
|---|---|---|---|---|
| Small SaaS | 1,000 | $22.50 | $21.25 | Gemini 2.5 Pro -$1.25 |
| Growing product | 10,000 | $225.00 | $212.50 | Gemini 2.5 Pro -$12.50 |
| Heavy usage | 100,000 | $2,250 | $2,125 | Gemini 2.5 Pro -$125.00 |
Which should you use?
For the typical chat-shape request (~1k input, 2k output), Gemini 2.5 Pro comes out 6% cheaper. If you're picking one as the default, that's usually the right choice on cost alone.
Context window differs: Gemini 2.5 Pro holds 2M of input vs 128K on the other side. If you regularly push past the smaller ceiling, the comparison ends there.
Heads-up: Gemini 2.5 Pro applies a long-context surcharge above 200K input tokens ($2.50 input / $15.00 output per 1M). Workloads that push past that threshold pay roughly 2x the numbers above.
Live cost calculator
Type in any token counts - both prices update instantly. Uses base input/output rates (no cache discount, no long-context tier).
GPT-4o
$0.0075
per request
Gemini 2.5 Pro
$0.0063
per request
Try both in the estimator →
Drop your actual prompt in, tokens are counted with the provider's own tokenizer, and the dollar number matches what lands on your invoice.
Frequently asked
- Which is cheaper, GPT-4o or Gemini 2.5 Pro?
- On a typical 1,000-input / 2,000-output request, Gemini 2.5 Pro costs ~$0.0213 vs ~$0.0225 on GPT-4o. Input or output rates can flip the answer for very lopsided workloads - see the cost ladder above.
- What's the difference in per-token pricing?
- GPT-4o charges $2.50 per 1M input tokens and $10.00 per 1M output tokens. Gemini 2.5 Pro charges $1.25 / $10.00 per 1M.
- Which has the bigger context window?
- Gemini 2.5 Pro is larger (2M) vs 128K on the other.
- Is there a cached-input discount on either?
- GPT-4o caches at $1.250 per 1M (50% off). Gemini 2.5 Pro caches at $0.125 per 1M (90% off). Workloads with repeated static prefixes see the biggest savings.
- Does Gemini 2.5 Pro have a long-context surcharge?
- Yes. Above 200K input tokens, Gemini 2.5 Pro bills at $2.50 input / $15.00 output per 1M instead of the standard rate.
- How fresh is this comparison?
- GPT-4o was re-verified on 2026-04-06 and Gemini 2.5 Pro on 2026-04-06 against each provider's published rate card. Calcis re-checks every row on a rolling schedule and re-deploys when a provider changes pricing.
GPT-4o verified 2026-04-06 · Gemini 2.5 Pro verified 2026-04-06. Rate cards at OpenAI and Google.