Gonka has started supporting DeepSeek V4 Flash 0731. The total computational scale is equivalent to approximately 2,000 H100 GPUs. The currently supported models are DeepSeek V4 Flash, Kimi-K2.6, and MiniMax-M2.7. Gonka aggregates GPU resources from around the world to provide a model invocation service compatible with OpenAI and Anthropic, allowing developers to specify models and send inference requests just like existing AI APIs. In the last 24 hours, the AI token processing volume reached 19.6 billion, with DeepSeek-related processing accounting for over 12 billion, which is more than 60% of the total. The official GonkaRouter page announces the support for DeepSeek V4 Flash and introduces the ability to invoke multiple AI models with a single API. The page includes a context window of 262,000 tokens, function call support, and private VPC deployment capabilities. GonkaRouter offers new users a $20 credit and presents a price of $0.0004 per million tokens. Actual costs may vary depending on the model, invocation method, and broker usage conditions. This announcement requires further confirmation regarding the impact of decentralized AI infrastructure on the cost structure for enterprise customers or developers.
This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.





























