Private AI
DeepSeek V4 Pro 0813 is the general-availability release of DeepSeek V4 Pro, built for coding, tool use, cybersecurity, automation, and long-horizon agent workflows. It supports a 1M-token context window and runs inside a TEE (Trusted Execution Environment), with provider attestation support. This route currently uses the base non-thinking mode.
Added Aug 16, 2026
Model weightsContext Window
1.0M
Max Output
1.0M
Input Price (Auto)
$1.39/1M
Output Price (Auto)
$4.16/1M
Cache Read (Auto)
$0.14/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
53.2
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
68.8
GPQA Diamond
Graduate-level scientific reasoning
92.8%
Better than 97% of models compared
HLE
Humanity's Last Exam
41.0%
Better than 94% of models compared
AA-LCR
Long context reasoning evaluation
75.3%
Better than 91% of models compared
SciCode
Python programming for scientific computing
49.2%
Better than 89% of models compared
Last updated Aug 16, 2026
Artificial Analysis