Deepseek V4 Pro 0813
DeepSeek V4 Pro 0813 is a chat model developed by DeepSeek, superseding a preview version. It is designed with enhanced agentic capabilities, particularly for production environments, and incorporates a DSpark speculative decoding module.
Input
Output
Context
1049K
Max Output
384K
Parameters
1650.5B
Technical Specifications
Model TypeChat
Context Window1,048,576 tokens
Max Output Tokens384,000 tokens
Parameters1650.5B
Release DateAug 13, 2026
Training CutoffNot available
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
41.0%
HLE
75.3%
AA-LCR
92.8%
GPQA
49.2%
SciCode
39.6%
Tau2 Banking
68.8
Coding
53.2
Intelligence
78.7%
Terminal-Bench 2.1
62.4
Speed (tok/s)
33.1
TTFA (s)
1.1
TTFT (s)
Resources & Links
More Models by DeepSeek
Deepseek V3.1 Base131K context · 684.5B · Open weightsDeepseek Prover V1.5 SFT4K context · 6.9B · Open weightsDeepseek V3.2 Speciale164K context · 685.4B · Open weightsDeepseek Math 7B Base4K context · 7B · Open weightsDeepseek R1 Distill Qwen 32B131K context · 32.8B · Open weightsDeepseek V3 Base131K context · 684.5B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 28, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.