DeepSeek V3 0324
DeepSeek released 2025-03-24
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +36.6 higher and costs 76% less ($0.105/M against $0.438/M) on this workload — and it does everything this model does.
Solar Pro 4 is cheaper still (88% less) but drops 164K → 131K max output.
Every price dimension
| Input | $0.250/M |
|---|---|
| Output | $1.00/M |
Independent scores
| Intelligence | 15.2 |
|---|---|
| Coding | 21.2 |
| Agentic | 1.6 |
| LMArena Elo | 1375default |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 164K |
|---|---|
| Max output | 164K |
| Input modes | text |
| Tool use | yes |
| Reasoning | no |
| Knowledge cutoff | 2024-07-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...