DeepSeek: DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro

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.

Modalities
In / out per 1M$1.60 / $3.20
Context1M
ReleasedApr 24, 2026

Providers

15 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
StreamLakefp8$0.95$1.90$0.081.49s40 tps100%
Baidu Qianfanfp8$1.69$3.38$0.141.05s51 tps100%
Cloudflare$1.15$2.55$0.201.82s39 tps100%
Azureeastus2$1.91$3.83$0.161.87s75 tps100%
DigitalOcean$1.04$2.09$0.211.04s61 tps100%
Venice$1.65$3.30$0.331.39s53 tps100%
Alibaba Cloud Int.us-east-1 · fp8$1.56$3.12$0.131.63s47 tps99.96%
NovitaAIfp8$1.60$3.20$0.142.22s60 tps99.95%
SiliconFlowfp8$1.00$3.13$0.141.32s40 tps99.95%
DeepInfraus · fp8$1.30$2.60$0.101.21s62 tps99.95%
Relacefp4$0.90$1.50$0.250.82s80 tps99.8%
AtlasCloudfp4$1.68$3.38$0.131.50s42 tps99.42%
GMICloudfp8$0.96$1.91$0.084.42s28 tps99.14%
Crusoefp8$1.74$3.48$0.150.91s49 tps97.61%
Alibaba Cloud Int.fp8$1.42$2.83$0.121.85s45 tps96.99%

Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek V4 Pro 0423 in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what DeepSeek V4 Pro 0423 costs pay-as-you-go elsewhere, not what you pay here.

Input
$1.60
per 1M tokens
Output
$3.20
per 1M tokens
Cache read
$0.14
per 1M cached tokens
Included in every pass
DeepSeek V4 Pro 0423 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 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
SiliconFlow Crusoe GMICloud StreamLake Alibaba Cloud Int. (us-east-1) Baidu Qianfan Alibaba Cloud Int. Relace AtlasCloud Venice Cloudflare Azure (eastus2) NovitaAI DeepInfra (us) DigitalOcean
0 tok/s250 tok/s500 tok/s750 tok/s1000 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
SiliconFlow Crusoe GMICloud StreamLake Alibaba Cloud Int. (us-east-1) Baidu Qianfan Alibaba Cloud Int. Relace AtlasCloud Venice Cloudflare Azure (eastus2) NovitaAI DeepInfra (us) DigitalOcean

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.22%
Oct 29, 6:00 PMNow
Availability over the last 24 hoursAvailability 98.82%
100% 95% 90% 85%
Oct 31, 6:10 PMNow

Apps

Tools that most often run DeepSeek V4 Pro 0423, by tokens this week.

Activity

2887.6B tokens processed market-wide in the last month.

050.0B100.0B150.0B200.0B
Oct 2Oct 7Oct 12Oct 17Oct 22Oct 27Nov 1
Tokens

FAQ

Which model id do I use for DeepSeek V4 Pro 0423?
deepseek/deepseek-v4-pro. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does DeepSeek V4 Pro 0423 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 0423 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $1.60 per 1M input tokens and $3.20 per 1M output tokens.
Who built DeepSeek V4 Pro 0423?
DeepSeek, in the DeepSeek family.

Explore

Other models your pass can call.