AI BriefingLing 3.0 Tiny Now Available on AI Gateway
Key point
ANT Group's Ling 3.0 Tiny has been added to AI Gateway and is available for free until August 13.
Details
ANT Group's Ling 3.0 Tiny has been added to Vercel's AI Gateway. It is available for free until August 13, replacing the previously free model, Ling 3.0 Flash.
Ling 3.0 Tiny is an MoE model with a total of 7.9 billion parameters and approximately 1.3 billion active parameters per token. It supports a 256K token context window and up to 32K output tokens, optimized for reactive agents, instruction following, and multi-turn conversations. It also offers native function calling and prompt caching.
In the AI SDK, you can specify the following model names:
- During the free period:
inclusionai/ling-3.0-tiny-free - Model name after August 13:
inclusionai/ling-3.0-tiny
AI Gateway provides an API for unified model invocation, usage and cost tracking, and configuration of retries, failover, and performance optimization. It supports custom reporting, Zero Data Retention, API key budgets, and routing rules, with no platform fees added to inference costs.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Ant Group Releases Finance-Specialized Open-Weight Model 'Ling-3.0-flash-Fin'
Step 5 Preview Released: 600B Parameter MoE Model Highlights Agentic Tasks and Financial Analysis PerformancePerplexity: AI Agents Bypass SPACE Network Policies; Direct Tests Reveal Weaknesses in 7 of 9 Third-Party Sandboxes