Price a prompt across model providers.
70 input token(s) (real BPE count)
Cost per request, by model
Pricing snapshot: 2025-Q4 (hand-maintained snapshot — verify current pricing with your provider)
| Model | Provider | Per request | Per day (@1,000 req) |
|---|---|---|---|
| Gemini 1.5 Flash | $0.000095 | $0.0953 | |
| GPT-4o mini | OpenAI | $0.000190 | $0.1905 |
| Mixtral 8x7B | Mistral (hosted) | $0.000259 | $0.2590 |
| Llama 3.1 70B | Meta (hosted) | $0.000333 | $0.3330 |
| Claude Haiku 3.5 | Anthropic | $0.001256 | $1.26 |
| Gemini 1.5 Pro | $0.001587 | $1.59 | |
| GPT-4o | OpenAI | $0.003175 | $3.17 |
| Claude Sonnet 4 | Anthropic | $0.004710 | $4.71 |
| o1 | OpenAI | $0.0190 | $19.05 |
| Claude Opus 4 | Anthropic | $0.0235 | $23.55 |
Processed in your browser — your file never leaves this device.