Alibaba
99.89%Context1M
Max output384K
p50 latency3,926 ms
Throughput75.0 t/s
Input price$0.66
Output price$1.98
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
deepseek/deepseek-v4-pro-0813
DeepSeek V4 Pro 0813
This is the 8/13 updated weights version of DeepSeek V4 Pro.
Input / 1M tokens$0.66
Output / 1M tokens$1.98
Maximum context1M
Inference providers10
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Baseten
99.58%Context1M
Max output384K
p50 latency2,782 ms
Throughput63.0 t/s
Input price$1.32
Output price$3.96
Zero retentionNo trainingCaching
Deepinfra
100.00%Context1M
Max output384K
p50 latency242 ms
Throughput91.0 t/s
Input price$1.3
Output price$2.6
Zero retentionNo trainingCaching
Deepseek
100.00%Context1M
Max output384K
p50 latency2,216 ms
Throughput79.0 t/s
Input price$0.66
Output price$1.98
Caching
Digitalocean
88.39%Context1M
Max output1M
p50 latency379 ms
Throughput43.5 t/s
Input price$1.32
Output price$3.96
Zero retentionNo trainingCaching
Fireworks
99.77%Context1M
Max output384K
p50 latency2,266 ms
Throughput74.0 t/s
Input price$1.32
Output price$3.96
Zero retentionNo trainingCaching
Gmicloud
98.68%Context1M
Max output384K
p50 latency1,951 ms
Throughput67.0 t/s
Input price$1.06
Output price$3.17
Caching
Novita
100.00%Context1M
Max output384K
p50 latency1,259 ms
Throughput72.0 t/s
Input price$1.32
Output price$3.96
No trainingCaching
Parasail
100.00%Context1M
Max output1M
p50 latency703 ms
Throughput80.0 t/s
Input price$1.32
Output price$3.96
Zero retentionNo trainingCaching
Streamlake
100.00%Context1M
Max output384K
p50 latency1,735 ms
Throughput144.0 t/s
Input price$1.32
Output price$3.96
Caching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 1M | 384K | 3,926 ms | 75.0 t/s | 99.895% | $0.66 | $1.98 | |
Baseten | 1M | 384K | 2,782 ms | 63.0 t/s | 99.582% | $1.32 | $3.96 | |
Deepinfra | 1M | 384K | 242 ms | 91.0 t/s | 100.000% | $1.3 | $2.6 | |
Deepseek | 1M | 384K | 2,216 ms | 79.0 t/s | 100.000% | $0.66 | $1.98 | |
Digitalocean | 1M | 1M | 379 ms | 43.5 t/s | 88.388% | $1.32 | $3.96 | |
Fireworks | 1M | 384K | 2,266 ms | 74.0 t/s | 99.768% | $1.32 | $3.96 | |
Gmicloud | 1M | 384K | 1,951 ms | 67.0 t/s | 98.684% | $1.06 | $3.17 | |
Novita | 1M | 384K | 1,259 ms | 72.0 t/s | 100.000% | $1.32 | $3.96 | |
Parasail | 1M | 1M | 703 ms | 80.0 t/s | 100.000% | $1.32 | $3.96 | |
Streamlake | 1M | 384K | 1,735 ms | 144.0 t/s | 100.000% | $1.32 | $3.96 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
Reasoning options
HighXhigh
Technical profile
- Model type
- Language model
- Release date
- Aug 12, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
deepseek/deepseek-v4-pro-0813Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.