DeepSeek
DeepSeek V4 Pro 0813
Released 2026-08-12
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
You send / 1M
$1.32
tokens in
It replies / 1M
$3.96
tokens out
Memory
1.05M
tokens it can read at once
Typical request
$0.0037
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 |
|---|---|---|---|---|
| Sail Research · fp4 | $0.450 | $0.800 | 100% | Read |
| Sail Research · fp4 | $0.450 | $0.800 | 100% | Read |
| DeepInfra · fp8 | $1.30 | $2.60 | 100% | Read |
| Ionstream | $0.370 | $2.93 | 100% | Read |
| Novita · fp8 | $0.990 | $2.97 | 100% | Read |
| DekaLLM | $1.08 | $3.80 | 99% | Read |
| BaseTen · fp4 | $1.32 | $3.96 | 93% | Read |
| Nebius · fp8 | $1.32 | $3.96 | 96% | Read |
| CoreWeave · fp8 | $1.31 | $3.96 | 97% | Read |
| Parasail · fp8 | $1.32 | $3.96 | 100% | Read |
| Together | $1.32 | $3.96 | 99% | Read |
| DigitalOcean | $1.32 | $3.96 | 100% | Read |
| SiliconFlow · fp8 | $1.32 | $3.96 | 99% | Read |
| Cloudflare | $1.32 | $3.96 | 99% | Read |
| Wafer · mxfp4 | $0.285 | $4.30 | 100% | Read |
| Phala | $1.45 | $4.36 | 95% | Read |
| Venice | $1.65 | $4.95 | 100% | Read |
| Relace · fp4 | $0.254 | $8.00 | 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: 393K tokens
- Repeated text is billed at $0.044 per 1M (prompt caching)
- Intelligence score: 36 / 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