Models / Compare /DeepSeek V4 Flash vs DeepSeek V4 Pro
Head to head
DeepSeek V4 Flash vs DeepSeek V4 Pro
Compared on live catalog data — pricing synced daily, benchmark scores with provenance.
The short version
- DeepSeek V4 Flash is cheaper to run hosted: $0.28/M output vs $0.87/M for DeepSeek V4 Pro (3.1× difference at the cheapest tracked provider).
- DeepSeek V4 Pro scores 71.57 on LiveBench vs 65.48 for DeepSeek V4 Flash.
- DeepSeek V4 Pro scores 42.63 on LiveBench Agentic Coding vs 37.63 for DeepSeek V4 Flash.
| Spec | ||
|---|---|---|
| Vendor | DeepSeek | DeepSeek |
| Parameters | 291B / 37B | 1.6T / 37B |
| 1M | 1M | |
| Weights | OPEN | OPEN |
| License | MIT License | MIT License |
| Modality | text->text | text->text |
| Released | Apr 22, 2026 | Apr 22, 2026 |
| 183.4 GBest | 1008 GBest | |
| Cheapest hosted | $0.14 / $0.28 per 1M (Novita AI) | $0.43 / $0.87 per 1M (OpenRouter) |
| Tracked providers | 32 | 23 |
DeepSeek V4 Flash — our take
DeepSeek V4 Flash is a large downloadable text model built for long documents, with a permissive MIT licence and a one-million-token request limit. Its measured web-development coding score is the strongest of its seven tracked skills, while creative writing is the weakest.
full breakdown →DeepSeek V4 Pro — our take
DeepSeek V4 Pro is a large downloadable text model with a one-million-token request limit and a permissive MIT licence. It excels at coding and hard-prompt tasks on the independent leaderboards we track, though its creative-writing score lags behind its other skills.
full breakdown →Need more columns? Use theinteractive comparison to add up to four models.