THE TICKER · HEAD-TO-HEAD · CHECKED DAILY · LAST CHANGE 2026-07-11
CLAUDE SONNET 5 VS DEEPSEEK V4 FLASH
Anthropic vs DeepSeek, in USD per million tokens, verified daily against public list prices. Same jobs, both meters running.
Claude Sonnet 5 costs 32.7x more than DeepSeek V4 Flash for the same job — a 1,000-token prompt with a 3,000-token reply runs $0.03 vs $0.0010. At 1,000 runs a day, that gap is $930.60 a month for identical traffic.
SIDE BY SIDE
| Claude Sonnet 5 → | DeepSeek V4 Flash → | |
|---|---|---|
| Vendor | Anthropic | DeepSeek |
| Input / MTok | $2.00 | $0.140 |
| Output / MTok | $10.00 | $0.280 |
| Output multiple | 5.0x | 2.0x |
| 1K prompt + 3K reply | $0.03 | $0.0010 |
SAME JOB, BOTH BILLS
| Scenario | Claude Sonnet 5 | DeepSeek V4 Flash | Gap |
|---|---|---|---|
| A typical prompt | $0.0096 | $0.0003 | 32.7x |
| A 20-turn conversation | $0.05 | $0.0017 | 28.6x |
| Summarizing a 10-page document | $0.05 | $0.0020 | 23.8x |
| One agent run | $0.12 | $0.0036 | 34.1x |
| A code review request | $0.04 | $0.0013 | 32.1x |
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 Claude Sonnet 5, DeepSeek V4 Flash and the other 10 models on the board — plus how much of it is waste either way.