OpenAI vs Gemini API Pricing
Compare current OpenAI and Gemini API pricing with practical model-level data for token costs and context windows.
Quick overview
The cheaper option depends on selected models, your input/output token mix, and context-window requirements.
Cheapest current OpenAI model
GPT-5 nano
Largest context window
1.05M
Cheapest current Google model
Gemini 2.5 Flash-Lite
Largest context window
1.05M
OpenAI
- Current models: 25
- Cheapest current model: GPT-5 nano
- Lowest input / 1M: $0.0500
- Lowest output / 1M: $0.4000
- Largest context window: 1.05M
- Current models: 6
- Cheapest current model: Gemini 2.5 Flash-Lite
- Lowest input / 1M: $0.1000
- Lowest output / 1M: $0.4000
- Largest context window: 1.05M
Current model pricing
| Provider | Model | Input / 1M | Output / 1M | Context window | Status | Source |
|---|---|---|---|---|---|---|
| OpenAI | GPT-5 nano | $0.0500 | $0.4000 | 400,000 | CURRENT | Source |
| Gemini 2.5 Flash-Lite | $0.1000 | $0.4000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-4.1 nano | $0.1000 | $0.4000 | 1,047,576 | CURRENT | Source |
| OpenAI | GPT-4o mini | $0.1500 | $0.6000 | 128,000 | CURRENT | Source |
| OpenAI | GPT-5.4 nano | $0.2000 | $1.2500 | 400,000 | CURRENT | Source |
| Gemini 3.1 Flash-Lite | $0.2500 | $1.5000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-5 mini | $0.2500 | $2.0000 | 400,000 | CURRENT | Source |
| Gemini 2.5 Flash | $0.3000 | $2.5000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-4.1 mini | $0.4000 | $1.6000 | 1,047,576 | CURRENT | Source |
| OpenAI | GPT-5.4 mini | $0.7500 | $4.5000 | 400,000 | CURRENT | Source |
| OpenAI | o1-mini | $1.1000 | $4.4000 | 128,000 | CURRENT | Source |
| OpenAI | o3-mini | $1.1000 | $4.4000 | 200,000 | CURRENT | Source |
| OpenAI | o4-mini | $1.1000 | $4.4000 | 200,000 | CURRENT | Source |
| Gemini 2.5 Pro | $1.2500 | $10.0000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-5 | $1.2500 | $10.0000 | 400,000 | CURRENT | Source |
| OpenAI | GPT-5.1 | $1.2500 | $10.0000 | 400,000 | CURRENT | Source |
| Gemini 3.5 Flash | $1.5000 | $9.0000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-5.2 | $1.7500 | $14.0000 | 400,000 | CURRENT | Source |
| Gemini 3.1 Pro | $2.0000 | $12.0000 | 1,048,576 | CURRENT | Source | |
| OpenAI | GPT-4.1 | $2.0000 | $8.0000 | 1,047,576 | CURRENT | Source |
| OpenAI | o3 | $2.0000 | $8.0000 | 200,000 | CURRENT | Source |
| OpenAI | GPT-4o | $2.5000 | $10.0000 | 128,000 | CURRENT | Source |
| OpenAI | GPT-5.4 | $2.5000 | $15.0000 | 1,050,000 | CURRENT | Source |
| OpenAI | GPT-5.5 | $5.0000 | $30.0000 | 1,050,000 | CURRENT | Source |
| OpenAI | GPT-5 pro | $15.0000 | $120.0000 | 400,000 | CURRENT | Source |
| OpenAI | o1 | $15.0000 | $60.0000 | 200,000 | CURRENT | Source |
| OpenAI | o3-pro | $20.0000 | $80.0000 | 200,000 | CURRENT | Source |
| OpenAI | GPT-5.2 pro | $21.0000 | $168.0000 | 400,000 | CURRENT | Source |
| OpenAI | GPT-5.4 pro | $30.0000 | $180.0000 | 1,050,000 | CURRENT | Source |
| OpenAI | GPT-5.5 pro | $30.0000 | $180.0000 | 1,050,000 | CURRENT | Source |
| OpenAI | o1-pro | $150.0000 | $600.0000 | 200,000 | CURRENT | Source |
Example cost comparison
| Scenario | Provider | Reference model | Estimated cost |
|---|---|---|---|
| 1K input + 1K output | OpenAI | GPT-5 nano | $0.0005 |
| 1K input + 1K output | Gemini 2.5 Flash-Lite | $0.0005 | |
| 10K input + 1K output | OpenAI | GPT-5 nano | $0.0009 |
| 10K input + 1K output | Gemini 2.5 Flash-Lite | $0.0014 | |
| 100K input + 5K output | OpenAI | GPT-5 nano | $0.0070 |
| 100K input + 5K output | Gemini 2.5 Flash-Lite | $0.0120 | |
| 1M input + 1M output | OpenAI | GPT-5 nano | $0.4500 |
| 1M input + 1M output | Gemini 2.5 Flash-Lite | $0.5000 |
Input price comparison
- OpenAI: lowest $0.0500, highest $150.0000
- Google: lowest $0.1000, highest $2.0000
Output price comparison
- OpenAI: lowest $0.4000, highest $600.0000
- Google: lowest $0.4000, highest $12.0000
Context window comparison
OpenAI largest context: 1.05M
Cheapest current model ≥100K: GPT-5 nano
Cheapest current model ≥1M: GPT-4.1 nano
Google largest context: 1.05M
Cheapest current model ≥100K: Gemini 2.5 Flash-Lite
Cheapest current model ≥1M: Gemini 2.5 Flash-Lite
Which provider should you consider?
Consider OpenAI for broad general-purpose model coverage. Consider Gemini when long context or Google model options are a key factor.
Compare with your own token usage
Open the calculator with these providers selected, then enter your expected input and output tokens.
Open calculatorFAQ
Is OpenAI or Google cheaper?
It depends on the specific model pair and your input/output token mix.
Why do input and output token prices differ?
Providers often price generated tokens differently from prompt tokens per model.
Which provider has the larger context window?
Use the context window comparison section to check current largest windows.
Can I compare these providers with other LLM APIs?
Yes. Open the full calculator and enable additional providers.
How do I calculate cost for my own token usage?
Open the calculator CTA and enter your projected input and output token totals.
Hosting your AI app?
After comparing API costs, the next cost factor is where your app runs. DigitalOcean can be a simple option for hosting prototypes, API backends, workers, databases, and Laravel apps.
Explore DigitalOcean →This link is an affiliate link. This means that, at zero cost to you, we earn commissions when you shop through the link.