DeepSeek: DeepSeek Pro Latest

deepseek/deepseek-pro-latest

This model always redirects to the latest model in the DeepSeek Pro family.

Modalities
In / out per 1M$0.23 / $8.00
Context1M
ReleasedSep 14, 2026

Providers

23 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Sail Researchus · fp4$0.90$0.58$0.191.54s78 tps100%
Sail Researchfp4$0.90$0.58$0.191.41s77 tps100%
StreamLake$0.66$1.98$0.022.02s44 tps100%
SiliconFlowfp8$1.32$3.96$0.042.10s53 tps100%
Phala$0.96$2.88$0.103.74s48 tps100%
GMICloudfp8$1.06$3.17$0.042.63s39 tps100%
Alibaba Cloud Int.us-east-1$1.32$3.96$0.131.47s61 tps100%
Baidu Qianfanfp8$1.32$3.96$0.041.19s41 tps100%
DigitalOcean$1.32$3.96$0.040.94s43 tps100%
DeepSeek$0.66$1.98$0.021.22s29 tps100%
Ionstream$0.37$2.93$0.090.97s59 tps99.97%
NovitaAIfp8$0.99$2.97$0.031.72s41 tps99.97%
Wafermxfp4$0.25$5.00$0.250.63s118 tps99.92%
DeepInfraus · fp8$1.30$2.60$0.101.48s47 tps99.89%
Cloudflare$1.32$3.96$0.041.95s35 tps99.67%
Together$1.32$3.96$0.130.71s101 tps99.66%
AtlasCloudfp8$1.32$3.96$0.131.39s44 tps99.33%
Parasailfp8$1.32$3.96$0.041.05s38 tps99.25%
Alibaba Cloud Int.$1.12$3.37$0.111.47s62 tps99.1%
DekaLLM$0.88$3.80$0.151.54s73 tps98.62%
Venice$1.65$4.95$0.171.53s47 tps98.48%
Relacefp4$0.23$8.00$0.231.26s48 tps97.69%
CoreWeavefp8$1.31$3.96$0.040.56s109 tps96.45%

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

Pricing

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

Input
$0.23
per 1M tokens
Output
$8.00
per 1M tokens
Cache read
$0.23
per 1M cached tokens
Included in every pass
DeepSeek Pro Latest 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 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Sail Research (us) Ionstream Together Relace DeepSeek SiliconFlow GMICloud Cloudflare Venice Phala Wafer Sail Research DigitalOcean Alibaba Cloud Int. AtlasCloud NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) DekaLLM
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Sail Research (us) Ionstream Together Relace DeepSeek SiliconFlow GMICloud Cloudflare Venice Phala Wafer Sail Research DigitalOcean Alibaba Cloud Int. AtlasCloud NovitaAI DeepInfra (us) CoreWeave Parasail StreamLake Baidu Qianfan Alibaba Cloud Int. (us-east-1) DekaLLM

Uptime

Share of requests that at least one provider served successfully.

Last 3 days
Oct 16, 11:00 AMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 18, 11:40 AMNow

Apps

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

No apps published

This measurement has not been published for the model yet. It appears as soon as it is.

Activity

Tokens processed market-wide.

No activity published

This measurement has not been published for the model yet. It appears as soon as it is.

FAQ

Which model id do I use for DeepSeek Pro Latest?
~deepseek/deepseek-pro-latest. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does DeepSeek Pro Latest 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 Pro Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.23 per 1M input tokens and $8.00 per 1M output tokens.
Who built DeepSeek Pro Latest?
DeepSeek, in the DeepSeek family.

Explore

Other models your pass can call.