deepseek-v4-pro
1458 ? DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
LLM & Generative AI 1 model 6 listings snapshot Oct 14, 2026, 12:54 AM
Platforms
click a card to open the detail tableModel variants
W3r9 dedup — same model + identical tags merge; prices are listed per billing form| Model | Provider | Tags | Input /1M | Output /1M |
|---|---|---|---|---|
| deepseek/deepseek-v4-pro | OpenRouter | 1M contextreasoning | $0.955 | $1.91 |
| deepseek-ai/DeepSeek-V4-Pro | DeepInfra | 1M contextreasoning | $1.30 | $2.60 |
| deepseek-v4-pro | DeepSeek | 1M contextreasoning | $0.660 | $1.98 |
| deepseek-v4-pro | DashScope | 1M contextreasoning | $1.78 | $3.56 |
| vanchin/deepseek-v4-pro | DashScope | 1M contextreasoning | $1.78 | $3.56 |
| deepseek/deepseek-v4-pro | Novita | 1M contextreasoning | $1.60 | $3.20 |
Capabilities
official design_arena & architecture metadataDesign Arena Elo official design_arena benchmark (OpenRouter)
Input / Output modalities modality: text->text
Platform details
per provider| provider | model | Input /1M | Output /1M | Latency ? | Official $/1M | Availability | Data time |
|---|---|---|---|---|---|---|---|
| DashScope | vanchin/deepseek-v4-pro | $1.78 | $3.56 | — | $0.660 | — | 2026-10-14 00:53:13 |
| DeepInfra | deepseek-ai/DeepSeek-V4-Pro-0813 | $1.30 | $2.60 | — | — | — | 2026-10-14 00:43:44 |
| DeepSeek Official | deepseek-v4-pro | $0.660 | $1.98 | 429.8 ms | $0.660 | 0% available | 2026-10-14 00:43:45 |
| Novita | deepseek/deepseek-v4-pro | $1.60 | $3.20 | — | $0.660 | — | 2026-10-14 00:54:15 |
| OpenRouter | deepseek/deepseek-v4-pro | $0.955 | $1.91 | 128.1 ms | $0.660 | 100% available | 2026-10-14 00:43:21 |
| Together | deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | — | — | — | 2026-10-14 00:53:13 |
6 rows · snapshot 2026-10-14 00:54:15 · from data/public/prices.json + measurements.json