DeepSeek: DeepSeek V4 Pro
Analysis Summary
DeepSeek: DeepSeek V4 Pro sits in the Specialist tier on our leaderboard, ranked #76 of 523 published models on overall intelligence. At $1.74 input and $3.48 output per 1M tokens, it is among the most expensive on the market. It offers an exceptionally large context window suited to long-document workflows and supports tool use and function calling.
Editorial notes
DeepSeek V4 Pro leads the agentic index across all 523 models, with top-tier GPQA, HLE, and a 1M token context window, plus tool use and function calling; a -4 regional penalty applies given limited enterprise accessibility.
Assessed April 24, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
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,..
Capabilities
Performance Indices
Source: Artificial Analysis
This model was released recently. Independent benchmark evaluations are typically completed within days of release — these figures are preliminary and are likely to be updated as testing is finalised.
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does DeepSeek: DeepSeek V4 Pro stack up?
Compare side-by-side with other specialist models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $1.74 | $0.001740 |
| Output | $3.48 | $0.003480 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
