Dispatch
Ling 3.0 Flash Fin, a 256K-context finance model, is free on Vercel AI Gateway until September 25
Inclusion AI's finance-tuned variant of Ling 3.0 Flash landed on AI Gateway on 2026-08-27 with a 256K-token context, 32K max output, and support for reasoning and function calling, aimed at multi-step research workflows that chain several tool calls before answering. Vercel exposes two IDs: `inclusionai/ling-3.0-flash-fin` continues on paid billing after the promotion, while `inclusionai/ling-3.0-flash-fin-free` deliberately errors out after September 25 so you cannot accidentally start paying. Coding agents can be pointed at it via `vercel ai-gateway coding-agents setup`.
↳ Follow the thread