DeepSeek
DeepSeek V4 Pro 0423
Released 2026-04-24
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,...
You send / 1M
$0.875
tokens in
It replies / 1M
$1.75
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0020
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Relace · fp4 | $0.900 | $1.50 | 100% | Read |
| DigitalOcean | $1.04 | $2.09 | 100% | Read |
| Cloudflare | $1.15 | $2.55 | 99% | Read |
| DeepInfra · fp8 | $1.30 | $2.60 | 100% | Read |
| SiliconFlow · fp8 | $1.50 | $3.13 | 100% | Read |
| Novita · fp8 | $1.60 | $3.20 | 99% | Read |
| Venice | $1.65 | $3.30 | 100% | Read |
| Crusoe · fp8 | $1.74 | $3.48 | 97% | Read |
| Azure | $1.91 | $3.83 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 384K tokens
- Repeated text is billed at $0.073 per 1M (prompt caching)
- Intelligence score: 30.4 / 100 (Artificial Analysis)
Similar models
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Zero Data Retention Long-Context AI ModelsTop No-Training Reasoning AI ModelsTop No-Training Reasoning Tool-Calling AI ModelsTop No-Training Reasoning Long-Context AI Models