DeepSeek Releases V4 Pro 0813 Model for Large-Scale Applications

Aug 12, 2026

AI Summary

DeepSeek has launched the V4 Pro 0813, a large-scale mixture-of-experts model. Released on August 12, 2026, it offers competitive pricing and is hosted by a single provider, ensuring direct request handling.

The DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model designed for various applications.
It was officially released on August 12, 2026, with a pricing structure of $0.435 per million tokens for input and $0.87 for output.
The model is hosted by one provider, OpenRouter, which manages requests directly without additional routing.
The model's performance metrics include throughput (tokens per second), latency (total round-trip time), and time-to-first-token (TTFT).
OpenRouter continuously monitors the model's performance, including success rates and standardized evaluation scores.
The model is compatible with OpenAI's API, allowing easy integration with existing SDKs by modifying the model slug.

deepseekai toolsproduct updatetechnology

DeepSeek Releases V4 Pro 0813 Model for Large-Scale Applications

Related Stories

OpenAI Releases ChatGPT Desktop Version for Linux Users

Automattic's Mesh CRM Launches on Android with Enhanced Features

Sandbar's Stream ring aims to revolutionize AI wearables with voice technology

Grok 4.6 Released with Enhanced Capabilities for Interactive and Visual Tasks