Vercel adds Thinking Machines’ Inkling 2 Small to AI Gateway

Vercel has added Thinking Machines’ Inkling 2 Small to AI Gateway, bringing a multimodal reasoning model for coding agents, visual understanding and professional knowledge work to the platform. The model accepts text and image inputs and produces text output.
- Inkling 2 Small is now available on Vercel AI Gateway.
- The model supports text and image inputs with text output.
- It can handle coding tasks, visual analysis and professional knowledge work.
- Developers can use it with Claude Code, Codex, Cursor and other agents.
- AI Gateway has no markup on provider pricing and no platform fee on inference.
A model for coding and visual tasks
According to Vercel, Inkling 2 Small can work through extended coding tasks and use tools to gather information. It can then turn that information into documents, spreadsheets and other deliverables, giving it a role beyond generating code from a single prompt.
The model can read text in images, interpret charts and infographics, and inspect interfaces. For visual development, it can use screenshots to check the output of code it has written and guide the next revision. These capabilities connect code generation with visual inspection, allowing an agent to assess an interface as part of its workflow.
How developers can access it
Developers can call the model through AI Gateway using the model name thinkingmachines/inkling-2-small. Vercel’s example uses the AI SDK and the streamText function to request a TypeScript function that groups tasks by status, then streams the response to standard output.
Inkling 2 Small is also available for agents including Claude Code, Codex and Cursor. Vercel says users should install the latest Vercel CLI and run npx vercel ai-gateway setup. After setup, they can select thinkingmachines/inkling-2-small in the agent. The company also directs users to its coding agents guide and model playground.
What AI Gateway provides
AI Gateway gives developers a unified API for calling models, tracking usage and cost, and configuring retries, failover and performance optimizations for higher-than-provider uptime, according to Vercel. The service also includes custom reporting, Zero Data Retention support, budgets for API keys and routing rules.
Vercel says AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including requests made through Bring Your Own Key, or BYOK. The addition of Inkling 2 Small therefore gives developers another model option within a service designed to centralize model access and operational controls, while the company’s model list shows the other language models available on AI Gateway.
Vercel: Inkling 2 Small now available on AI Gateway


