Source: vercel.com/changelog/longcat-2-5-now-available-on-ai-gateway
Vercel has added LongCat 2.5, a model from Meituan, to AI Gateway. Meituan describes it as combining native visual understanding with coding and multi-step tool use. The model accepts text and image inputs and has a 1M-token context window for code, documents and long task histories.
Meituan highlights gains in visual programming, creative design and 3D tasks, along with longer agent workflows that carry engineering work from planning through execution. Developers can call the model in the AI SDK with the identifier meituan/longcat-2.5. For coding agents such as Claude Code, Codex and Cursor, Vercel says to install the latest Vercel CLI, run npx vercel ai-gateway setup, and then select meituan/longcat-2.5 in the agent.
AI Gateway provides a unified API for calling models and tracking usage and cost, with retries, failover and performance settings aimed at uptime above that of individual providers. It also includes custom reporting, Zero Data Retention support, budgets for API keys and routing rules. Vercel says it reflects provider pricing with no markup and charges no platform fee on inference, including Bring Your Own Key requests.
Why it matters if you build agents
Teams already using AI Gateway can try LongCat 2.5 for coding and tool-heavy agent work by changing the model name to meituan/longcat-2.5. Because the gateway adds no markup or inference platform fee, the model's cost can be compared directly with provider pricing. Check the text and image input types and the 1M-token context window against your workload before routing production traffic to it.
Get stories like this every weekday
One short email with the day's agent tooling news.