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$0.12 / $4.00
Context1M
ReleasedAug 12, 2026
Providers
26 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.68 | $1.20 | $0.10 | 0.38s | 67 tps | 100% | |
| $0.68 | $1.20 | $0.10 | 0.35s | 63 tps | 100% | |
| $0.66 | $1.98 | $0.02 | 1.75s | 43 tps | 100% | |
| $0.37 | $2.93 | $0.09 | 0.65s | 31 tps | 100% | |
| $0.99 | $2.97 | $0.03 | 1.66s | 36 tps | 100% | |
| $0.96 | $2.88 | $0.10 | 3.19s | 52 tps | 100% | |
 Basetenfp4 | $1.32 | $3.96 | $0.13 | 0.75s | 47 tps | 100% |
 DeepInfraus · fp8 | $1.30 | $2.60 | $0.10 | 0.95s | 44 tps | 99.97% |
| $1.32 | $3.96 | $0.04 | 1.32s | 61 tps | 99.97% | |
| $1.32 | $3.96 | $0.04 | 1.19s | 29 tps | 99.96% | |
| $0.66 | $1.98 | $0.07 | 1.11s | 23 tps | 99.93% | |
 CoreWeavefp8 | $1.31 | $3.96 | $0.04 | 0.52s | 117 tps | 99.92% |
 SiliconFlowfp8 | $1.32 | $3.96 | $0.04 | 1.53s | 21 tps | 99.89% |
| $0.88 | $3.80 | $0.15 | 0.96s | 39 tps | 99.88% | |
| $0.12 | $4.00 | $0.11 | 0.28s | 86 tps | 99.82% | |
| $0.28 | $4.30 | $0.28 | 0.27s | 76 tps | 99.8% | |
| $0.10 | $8.00 | $0.10 | 0.54s | 36 tps | 99.8% | |
| $1.32 | $3.96 | $0.13 | 1.39s | 22 tps | 99.77% | |
| $0.58 | $1.74 | $0.06 | 1.08s | 27 tps | 99.62% | |
| $1.32 | $3.96 | $0.13 | 0.53s | 92 tps | 99.52% | |
| $1.06 | $3.17 | $0.04 | 3.50s | 55 tps | 99.38% | |
 DigitalOcean | $1.32 | $3.96 | $0.04 | 1.35s | 41 tps | 99.33% |
| $1.32 | $3.96 | $0.04 | 0.48s | 39 tps | 99.29% | |
| $1.65 | $4.95 | $0.17 | 1.12s | 29 tps | 98.85% | |
| $1.32 | $3.96 | $0.04 | 0.44s | 69 tps | 95.92% | |
 DeepSeek | $0.66 | $1.98 | $0.02 | 1.09s | 71 tps | 91.9% |
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
$0.12
per 1M tokens
Output
$4.00
per 1M tokens
Cache read
$0.11
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.
0.0s20.0s40.0s60.0s80.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Sail Research (us) Ionstream Wafer (us) Together Baseten Relace DeepSeek SiliconFlow DekaLLM GMICloud Cloudflare Wafer Sail Research DigitalOcean Alibaba Cloud Int. AtlasCloud Nebius Token Factory NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) Phala Venice
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
Sail Research (us) Ionstream Wafer (us) Together Baseten Relace DeepSeek SiliconFlow DekaLLM GMICloud Cloudflare Wafer Sail Research Alibaba Cloud Int. AtlasCloud Nebius Token Factory NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) Phala Venice DigitalOcean
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.21%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 98.25%
100% 95% 90% 85%
Oct 31, 6:10 PMNow
Apps
Tools that most often run DeepSeek V4 Pro 0813, by tokens this week.
Activity
4216.5B tokens processed market-wide in the last month.
0100.0B200.0B300.0B400.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
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 https://minuykh.app/v1.
How much context does DeepSeek V4 Pro 0813 hold?
1,048,576 tokens per request, of which up to 943,718 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 $0.12 per 1M input tokens and $4.00 per 1M output tokens.
Who built DeepSeek V4 Pro 0813?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
