DeepSeek V4 Pro 0813 pricing & price history
DeepSeek V4 Pro 0813 by DeepSeek costs $0.46 per 1M input tokens and $1.39 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.39 input / $1.39 output.
Price history
No price changes since tracking began on 2026-09-24. We check hourly.
Providers serving DeepSeek V4 Pro 0813 (24)
| Provider | Input | Output | Context | Uptime 30m | Uptime 24h |
|---|---|---|---|---|---|
| Wafer | $0.39 | $2.90 | 1M | 100.0% | 99.8% |
| Sail Research fp4 | $0.40 | $4.30 | 1M | 100.0% | 99.7% |
| Sail Research fp4 | $0.40 | $4.30 | 1M | 100.0% | 99.8% |
| StreamLake | $0.46 | $1.39 | 1M | 99.9% | 99.8% |
| Ionstream | $0.50 | $2.30 | 1M | 99.9% | 99.7% |
| DeepSeek | $0.66 | $1.98 | 1M | 100.0% | 99.9% |
| Novita fp8 | $0.99 | $2.97 | 1M | 100.0% | 99.7% |
| NextBit fp8 | $1.06 | $3.17 | 1M | 100.0% | 99.0% |
| GMICloud fp8 | $1.06 | $3.17 | 1M | 99.7% | 99.8% |
| Alibaba | $1.12 | $3.37 | 1M | 100.0% | 100.0% |
| DeepInfra fp8 | $1.30 | $2.60 | 1M | 100.0% | 99.2% |
| CoreWeave fp8 | $1.31 | $3.96 | 1M | 100.0% | 100.0% |
| AtlasCloud fp8 | $1.32 | $3.96 | 1M | 100.0% | 99.8% |
| Baidu fp8 | $1.32 | $3.96 | 1M | 100.0% | 99.9% |
| BaseTen fp4 | $1.32 | $3.96 | 1M | 99.5% | 98.7% |
| Parasail fp8 | $1.32 | $3.96 | 1M | 100.0% | 99.8% |
| Together | $1.32 | $3.96 | 1M | 100.0% | 99.1% |
| DigitalOcean | $1.32 | $3.96 | 1M | 100.0% | 99.8% |
| SiliconFlow fp8 | $1.32 | $3.96 | 1M | — | 98.6% |
| BaseTen fp4 | $1.32 | $3.96 | 1M | 98.4% | 97.5% |
| Cloudflare | $1.32 | $3.96 | 1M | — | 91.3% |
| Fireworks | $1.32 | $3.96 | 1M | 67.4% | 98.8% |
| Phala | $1.45 | $4.36 | 1M | — | 99.2% |
| Venice | $1.65 | $4.95 | 1M | 99.9% | 98.9% |
Provider availability updated 55m ago.
Cost calculator
Cheaper alternatives to DeepSeek V4 Pro 0813
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
D DeepSeek V4 Flash 0731 DeepSeek | $0.04 | $0.32 | 1.3M | 34.3 | compare |
O GPT-6 Luna OpenAI | $0.10 | $0.50 | 1.1M | 37.3 | compare |
D DeepSeek V4.1 Flash DeepSeek | $0.14 | $0.42 | 1M | 39.5 | compare |
Z GLM 5.3 Flash Z.ai (Zhipu) | $0.15 | $0.50 | 1.3M | 41.8 | compare |
O GPT-5.6 Luna OpenAI | $0.20 | $1.20 | 1.1M | 37.3 | compare |
M MiniMax M3 MiniMax | $0.30 | $1.20 | 1M | 29.2 | compare |
X MiMo-V2.6-Pro Xiaomi | $0.43 | $0.87 | 1M | 46.3 | compare |
X MiMo-V2.5-Pro Xiaomi | $0.43 | $0.87 | 1.1M | 26 | compare |
About DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
FAQ
How much does DeepSeek V4 Pro 0813 cost?
DeepSeek V4 Pro 0813 by DeepSeek costs $0.46 per 1M input tokens and $1.39 per 1M output tokens, with a 1M token context window. The cheapest provider currently charges $0.39 input / $1.39 output. A typical request with 2,000 input and 500 output tokens costs about $0.0016.
What is the context window of DeepSeek V4 Pro 0813?
DeepSeek V4 Pro 0813 supports up to 1,048,576 tokens of context and up to 384,000 output tokens per request.
Has DeepSeek V4 Pro 0813’s price changed?
No price changes recorded since ModelBank started tracking it on 2026-09-24.
Is DeepSeek V4 Pro 0813 being deprecated?
No retirement date has been announced for DeepSeek V4 Pro 0813 as of 2026-09-24.
What are cheaper alternatives to DeepSeek V4 Pro 0813?
Cheaper options include DeepSeek V4 Flash 0731 ($0.04/$0.32), GPT-6 Luna ($0.10/$0.50), DeepSeek V4.1 Flash ($0.14/$0.42), GLM 5.3 Flash ($0.15/$0.50).