DeepSeek: DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Modalities
In / out per 1M$1.32 / $3.96
Context1M
ReleasedAug 12, 2026
Providers
22 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.15 | $8.00 | $0.15 | — | — | 100% | |
| $0.16 | $0.49 | $0.01 | 0.95s | 34 tps | 100% | |
 DeepSeek | $0.66 | $1.98 | $0.02 | 1.30s | 49 tps | 100% |
 CoreWeavefp8 | $1.31 | $3.96 | $0.04 | 0.44s | 70 tps | 100% |
 DigitalOcean | $1.32 | $3.96 | $0.04 | 0.55s | 43 tps | 100% |
 SiliconFlowfp8 | $1.32 | $3.96 | $0.04 | 1.30s | 33 tps | 100% |
| $1.32 | $3.96 | $0.04 | 2.56s | 38 tps | 100% | |
| $0.99 | $2.97 | $0.03 | 1.36s | 35 tps | 99.95% | |
| $1.06 | $3.17 | $0.04 | 2.40s | 38 tps | 99.95% | |
| $1.32 | $3.96 | $0.04 | 0.61s | 58 tps | 99.92% | |
| $0.25 | $3.00 | $0.20 | 0.48s | 68 tps | 99.89% | |
| $0.66 | $1.98 | $0.02 | 1.73s | 44 tps | 99.89% | |
| $0.96 | $2.88 | $0.10 | 3.33s | 48 tps | 99.89% | |
| $0.66 | $1.98 | $0.07 | 1.23s | 29 tps | 99.88% | |
| $0.48 | $1.98 | $0.10 | 1.19s | 46 tps | 99.77% | |
| $0.48 | $1.98 | $0.10 | 1.19s | 47 tps | 99.68% | |
| $1.32 | $3.96 | $0.13 | 0.72s | 59 tps | 99.63% | |
 DeepInfraus · fp8 | $1.30 | $2.60 | $0.10 | 1.93s | 40 tps | 99.42% |
| $1.32 | $3.96 | $0.13 | 1.31s | 37 tps | 99.42% | |
| $0.37 | $2.93 | $0.09 | 0.67s | 42 tps | 98.99% | |
| $0.58 | $1.74 | $0.06 | 1.16s | 41 tps | 98.35% | |
| $1.65 | $4.95 | $0.17 | 2.53s | 28 tps | 97.44% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Pro 0813 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek V4 Pro 0813 costs pay-as-you-go elsewhere, not what you pay here.
Input
$1.32
per 1M tokens
Output
$3.96
per 1M tokens
Cache read
$0.04
per 1M cached tokens
Included in every pass
DeepSeek V4 Pro 0813 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s10.0s20.0s30.0s40.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Sail Research (us) Ionstream Together DeepSeek SiliconFlow GMICloud Phala Wafer Sail Research Alibaba Cloud Int. AtlasCloud NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) Cloudflare DigitalOcean Venice Relace
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Sail Research (us) Ionstream Together DeepSeek SiliconFlow GMICloud Phala Wafer Sail Research Alibaba Cloud Int. AtlasCloud NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) DigitalOcean Venice Cloudflare Relace
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.78%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.82%
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run DeepSeek V4 Pro 0813, by tokens this week.
Activity
4538.1B tokens processed market-wide in the last month.
0100.0B200.0B300.0B400.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for DeepSeek V4 Pro 0813?
deepseek/deepseek-v4-pro-0813. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek V4 Pro 0813 hold?
1,048,576 tokens per request, of which up to 393,216 can be the response.
What can it accept and return?
Input: text. Output: text.
What does DeepSeek V4 Pro 0813 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.32 per 1M input tokens and $3.96 per 1M output tokens.
Who built DeepSeek V4 Pro 0813?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
