← DeepSeek V4 Pro · API · Max effort
Evidenceacceptedpricing_page
Official product pricing
Artificial Analysis — DeepSeek V4 Pro (max) first-party pricing
ev_2026_07_dsv4pro_pricing
Result
0.435
Confidence A
- Tested
- 2026-07-11
Configuration
How it was measured
- Exact model
- deepseek-v4-pro
- Reasoning
- max
- Tool access
- n/a
- Prompting
- n/a
Caveats
Known limitations
- List price; max-effort verbosity multiplies real task cost.
- Flash tier is a different Build (not this sheet).
Weighting
Evidence weight factors
The engine weights each evidence row by these factors (0–1) when fusing scores — higher is more trusted.
relevance1.00
quality0.80
recency1.00
health1.00
comparability0.95
reliability0.90
Benchmark
Official product pricing
Official per-token API pricing from the provider pricing page.
Benchmark source →