DeepSeek V4 Proon Krater.ai
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. It is designed for advanced reasoning, coding,
Released April 24, 2026
Specifications
DeepSeek V4 Pro at a glance
Context
1M tokens
Max output
384K tokens
Input
Text
Output
Text
Input price
$0.43 / 1M
Output price
$0.87 / 1M
Krater rank
#15
Capabilities
What it is good at
Catalog capabilities
- Generates text responses
- Supports tool calling
- Supports structured outputs
Good for
Benchmarks
Catalog data, not Krater benchmarks.
Coding index score
59.4
Agentic index score
36.4
Intelligence index score
44.3
Design Arena 3d rank
#10
Design Arena gamedev rank
#21
Compare
Compare DeepSeek V4 Pro
DeepSeek V4 Pro vs DeepSeek V4 Flash
V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window.
Open comparisonDeepSeek V4 Pro vs DeepSeek V3.2 Exp
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
Open comparisonDeepSeek V4 Pro vs Chat
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions.
Open comparisonFAQ
Questions about DeepSeek V4 Pro
Clear answers based on the model catalog and Krater access.
Use DeepSeek V4 Pro in your API
Connect with Krater's unified API.
Ready to use DeepSeek V4 Pro?
Access leading models in one focused workspace.