Ramp Launches Router for Multi-Model AI Access
Ramp has launched Router, an AI model routing service that allows users and companies to access and switch between multiple large language models. The service is available through an API.
Search
Tag: #llm-api6 results
Xiaomi: The Token Price Butcher
Xiaomi has significantly reduced its token pricing, positioning itself as a disruptive force in the AI infrastructure market. This move aims to make high-volume AI usage more accessible and cost-effective for developers.
DeepSeek Slashes Input Cache Prices 90%
DeepSeek reduced input cache hit prices across all API services to 1/10th starting April 26. Pro models add 2.5-fold discount until May 5, 2026. V4-Pro now costs 0.025 CNY/million tokens, V4-Flash 0.02 CNY/million tokens.
DeepSeek API Cache Pricing Drops to 1/10th
DeepSeek officially cuts input cache hit prices across all APIs to 1/10th of launch rates. Post-discount, V4-Pro cached input hits 0.025 CNY/million tokens, a global large model low. Adjustment targets V4-Pro and V4-Flash series in cache-hit scenarios.
Building apps with Doubao API is highly addictive
The article highlights the ease and efficiency of using the Doubao AI model to build custom applications. It emphasizes the 'teach a man to fish' philosophy of leveraging AI tools for rapid development.
PFN Launches PLaMo 3.0 Prime with Free API Plan
Preferred Networks has officially released PLaMo 3.0 Prime, a full-scratch Japanese AI model. The company emphasizes high cost-performance and includes a free API tier for developers.