gpt-5 vs gpt-5-mini
OpenAI against OpenAI, priced on the same four workloads with price book 2026-10-22.
On real workloads
| Workload | gpt-5 per call | gpt-5-mini per call | Monthly difference |
|---|---|---|---|
| Chat reply 1,500 input and 400 output tokens, 100,000 calls a month |
$0.00588 | $0.00118 | −$470.00 |
| RAG answer, cached context 2,000 fresh + 4,000 cached input, 500 output, 100,000 calls a month |
$0.008 | $0.0016 | −$640.00 |
| Agent step 4,000 fresh + 8,000 cached input, 800 output, 250,000 calls a month |
$0.01 | $0.0028 | −$2,800.00 |
| Batch summary 3,000 input and 300 output tokens via the Batch API, 1,000,000 calls a month |
$0.00337 | $0.000675 | −$2,700.00 |
Monthly difference is gpt-5-mini minus gpt-5. Batch rows use each provider's Batch API rates where published. Price both on your own workload.
Rates
| Model | Input | Output | Cache read | Cache write | Context |
|---|---|---|---|---|---|
| openai/gpt-5 | $1.25 | $10.00 | $0.125 | — | 272K |
| openai/gpt-5-mini | $0.25 | $2.00 | $0.025 | — | 272K |
Price is one input. Before switching, run your own prompts through both and compare quality; then veqen diff prices the change at your production volume.