DeepSeek-V4 Pro now available on Together AI

2026-04-29 · Source: Together AI | The AI Native Cloud - Together.ai · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure · Depth: Advanced, medium

Summary

DeepSeek-V4 Pro, a 1.6T-parameter Mixture-of-Experts (MoE) reasoning model with 49B activated parameters, is now available on Together AI. It offers a 512K-token context window for long-context workloads, with a model-level context of 1M tokens. The model features controllable reasoning modes—Non-Think, Think High, and Think Max—allowing users to balance response speed with reasoning depth. Pricing is set at \$2.10 per 1M input tokens, \$0.20 per 1M cached input tokens, and \$4.40 per 1M output tokens, providing a 90% cost reduction for reused context. DeepSeek-V4 Pro is designed for demanding tasks like code agents, document intelligence, and research synthesis, and can be deployed via Serverless Inference or Monthly Reserved infrastructure on Together AI.

Key takeaway

For AI Engineers building long-context applications, DeepSeek-V4 Pro on Together AI offers a robust solution. You can utilize its 512K context window for complex tasks like code agents or document intelligence. Employ the controllable reasoning modes to optimize performance and cost per workload. Implement cached input pricing to significantly reduce expenses for repeated analysis over stable contexts. Consider Serverless for development and Reserved for production needs.

Key insights

DeepSeek-V4 Pro offers scalable, cost-effective long-context reasoning with flexible deployment and controllable reasoning modes.

Principles

• Match reasoning depth to task complexity.
• Cache stable contexts for cost savings.
• Hybrid attention optimizes long-context serving.

In practice

• Use Non-Think for simple extraction tasks.
• Apply Think Max for deep research synthesis.
• Cache large document sets for repeated queries.

Topics

• DeepSeek-V4 Pro
• Mixture-of-Experts
• Long-Context AI
• Together AI
• Serverless Inference
• Cached Input Pricing
• Reasoning Modes

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, Machine Learning Engineer, MLOps Engineer

Related on AIssential

• DeepSeek-V4: a million-token context that agents can actually use — DeepSeek V4 optimizes large language models for agentic workflows through architectural and training innovations.
• DeepSeek V4: One Million Tokens, Three Thinking Modes, and the First Real Hands-On Reports — DeepSeek-V4 optimizes long-context LLMs via novel attention and training stability, offering tiered reasoning and cost-effective variants.
• 🥇Top AI Papers of the Week — DeepSeek V4 pushes open-source LLMs to million-token contexts with novel attention and training stability techniques.
• DeepSeek launches V4 model with one million token context — DeepSeek-V4 offers enhanced AI capabilities, including a one-million-token context, optimized for domestic chips.
• DeepSeek V4 AI Beats Billion Dollar Systems…For Free — DeepSeek 4 achieves massive context windows and efficiency through multi-layered KV-cache compression.
• As agentic AI pushes rivals to raise prices and cap usage, Deepseek ships a good-enough model for almost nothing — Deepseek's V4 models offer massive context windows and competitive performance at significantly reduced costs via architectural innovation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Together AI | The AI Native Cloud - Together.ai.