Ling 3.0 Flash Fin now available on AI Gateway for free
Ling 3.0 Flash Fin adds a finance-focused reasoning and tool-calling option to AI Gateway, with separate model IDs for automatic billing or a hard stop after the free period.
Ling 3.0 Flash Fin is free through **September 25** on AI Gateway. It has a **256K-token context window**, supports up to **32K output tokens**, reasoning, function calling, and multi-tool financial research workflows.
Choose the model ID according to cost behavior: inclusionai/ling-3.0-flash-fin continues at standard pricing, while **inclusionai/ling-3.0-flash-fin-free** stops with an error after the offer. Either can be selected for a coding agent after AI Gateway setup.
Ling 3.0 Flash Fin is free through **September 25** on AI Gateway. It has a **256K-token context window**, supports up to **32K output tokens**, reasoning, function calling, and multi-tool financial research workflows. Choose the model ID according to cost behavior: inclusionai/ling-3.0-flash-fin continues at standard pricing, while **inclusionai/ling-3.0-flash-fin-free** stops with an error after the offer. Either can be selected for a coding agent after AI Gateway setup. The material gives capability limits but no quality, latency, or cost comparison. The model’s specialization is financial analysis, so its value for general coding work remains untested here.
This adds a temporary, finance-specialized evaluation route rather than evidence for a new general coding default. Its 256K context, 32K output, reasoning, and multi-tool support make financial-agent trials concrete, while the two model IDs force an explicit continuity choice after September 25. The absence of comparative quality, latency, and cost data keeps selection workload-specific.