AI Cost Estimator
Calculate API costs for GPT-4, Claude, Gemini — per request and monthly
Per Request$0.007500
Daily (100 reqs)$0.7500
Monthly Estimate$22.50
Cost Breakdown
Input (1000 tokens)$0.002500
Output (500 tokens)$0.005000
Total per request$0.007500
All Models — Live Pricing (per 1M tokens)
10 models| Model | Provider | Input / 1M | Output / 1M | Context |
|---|---|---|---|---|
| GPT-4o | OpenAI | $2.5 | $10 | 128K |
| GPT-4o Mini | OpenAI | $0.15 | $0.6 | 128K |
| GPT-4 Turbo | OpenAI | $10 | $30 | 128K |
| o1 | OpenAI | $15 | $60 | 200K |
| Claude Opus 4 | Anthropic | $15 | $75 | 200K |
| Claude Sonnet 4 | Anthropic | $3 | $15 | 200K |
| Claude Haiku 3.5 | Anthropic | $0.25 | $1.25 | 200K |
| Gemini 2.0 Flash | $0.1 | $0.4 | 1M | |
| Gemini Pro 1.5 | $1.25 | $5 | 1M | |
| Llama 3.3 70B | Meta | $0.12 | $0.3 | 128K |
Frequently Asked Questions
Where does the pricing data come from?
Pricing is fetched live from the OpenRouter public API which aggregates pricing from OpenAI, Anthropic, Google, Meta, and more. Data is cached for 24 hours. Click "Refresh Prices" to force an update.
How do I know my token count?
Use our Token Counter tool to estimate tokens from your actual prompts. A rough rule of thumb: 1 token ≈ 4 characters in English.
Why does the model list vary?
OpenRouter's catalogue changes as providers release new models and deprecate old ones. The list you see reflects what's currently available via their API.