DeepSeek-V4 Pro model with 1.6T parameters now on Together AI

DeepSeek-V4 Pro, a large Mixture-of-Experts model with 1.6 trillion parameters, is now accessible on the Together AI platform. This model is designed for long-context reasoning, supporting up to a 512K-token context window in its initial Together AI deployment, with plans for a 1M-token context window. It features controllable reasoning modes to optimize for speed or depth and offers specialized pricing for cached input tokens to reduce costs on repeated queries. AI

IMPACT Enables new applications requiring reasoning over extensive datasets, potentially lowering costs for repeated long-context queries.

RANK_REASON This is a significant release of a large-scale model with advanced long-context capabilities made available on a cloud platform. [lever_c_demoted from significant: ic=1 ai=1.0]

Read on Together AI blog →

• CorpusQA 1M
• DeepSeek
• DeepSeek V3.2
• DeepSeek V4 Flash
• DeepSeek-V4 Pro
• GPQA Diamond
• LiveCodeBench
• Mixture-of-Experts
• MRCR 1M
• SWE-bench Verified
• Together AI

• model release
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →