Inkling Small from Thinking Machines is now available on AI Gateway
By Steven Van ·
Inkling Small from Thinking Machines is now available on AI Gateway.
Vercel's AI Gateway now offers Inkling Small from Thinking Machines. The model reaches performance comparable to the larger Inkling model at about a quarter of the size, using much less compute per task. It's a generalist with native reasoning over audio and images, and holds up on reasoning, agentic coding, and tool use.
- Thinking effort is controllable, from minimal to maximum, to trade quality against cost and latency.
- For visual tasks it can crop, zoom, and inspect images programmatically, useful for documents and charts where the relevant detail is small.
- It's used by setting the model to thinkingmachines/inkling-small in the AI SDK.
- It supports Zero Data Retention, turned on team-wide from the dashboard or per request with zeroDataRetention: true, which routes requests only to providers that delete prompts and responses after each request.
- Coding agents can be connected to it by running vercel ai-gateway coding-agents setup and selecting thinkingmachines/inkling-small in the agent's model configuration.
AI Gateway reflects provider pricing with no markup and charges no platform fee on inference, including on Bring Your Own Key requests.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →