THE TICKER · HEAD-TO-HEAD · CHECKED DAILY · LAST CHANGE 2026-10-13
GPT-5 MINI VS DEEPSEEK V4 PRO
OpenAI vs DeepSeek, in USD per million tokens, cross-checked daily against the public pricing dataset. Same jobs, both meters running.
DeepSeek V4 Pro costs 1.1x more than GPT-5 Mini for the same job — a 1,000-token prompt with a 3,000-token reply runs $0.0066 vs $0.0063. At 1,000 runs a day, that gap is $10.50 a month for identical traffic.
SIDE BY SIDE
| GPT-5 Mini → | DeepSeek V4 Pro → | |
|---|---|---|
| Vendor | OpenAI | DeepSeek |
| Input / MTok | $0.250 | $0.660 |
| Output / MTok | $2.00 | $1.98 |
| Output multiple | 8.0x | 3.0x |
| 1K prompt + 3K reply | $0.0063 | $0.0066 |
SAME JOB, BOTH BILLS
| Scenario | GPT-5 Mini | DeepSeek V4 Pro | Gap |
|---|---|---|---|
| A typical prompt | $0.0019 | $0.0020 | 1.1x |
| A 20-turn conversation | $0.0090 | $0.01 | 1.2x |
| Summarizing a 10-page document | $0.0084 | $0.01 | 1.4x |
| One agent run | $0.02 | $0.03 | — |
| A code review request | $0.0079 | $0.0084 | 1.1x |
Output sizes use the same editorial ratios as the Burn Calculator. Estimates, not invoices — and price is not a benchmark: the cheaper model is only a bargain if it does the job.
SETTLE IT WITH YOUR OWN PROMPT
Paste a real prompt into the Burn Calculator and see what it costs on GPT-5 Mini, DeepSeek V4 Pro and the other 34 models on the board — plus how much of it is waste either way.