Inkling Small model now available on AI Gateway
Inkling Small from Thinking Machines is now integrated into AI Gateway, offering comparable performance to larger models at a quarter of the size with lower compute costs. The model supports audio and image reasoning, tool use, and controllable thinking effort to balance quality against latency and cost.
from Thinking Machines is now available on AI Gateway.Inkling Small
Inkling Small reaches performance comparable to the larger Inkling model at about a quarter of the size, using much less compute per task. It is a broad generalist with native reasoning over audio and images, and it holds up well on reasoning, agentic coding, and tool use. Controllable thinking effort lets you trade quality against cost and latency, from minimal to maximum reasoning.
For visual tasks, it can crop, zoom, and inspect images programmatically, which helps on documents and charts where the relevant detail is small.
To use Inkling, set to in the :modelthinkingmachines/inkling-smallAI SDK
Inkling-Small is compatible with . Turn it on team-wide from the dashboard, or per request with , and AI Gateway routes only to providers that delete prompts and responses after each request.Zero Data RetentionzeroDataRetention: true
Inkling-Small is also a cost-efficient choice for coding and tool-use workflows. Run to connect your coding agents to AI Gateway, then select in the agent's model configuration. See the .vercel ai-gateway coding-agents setupthinkingmachines/inkling-smallcoding agents guide
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on (BYOK) requests. Try Inkling Small in the .Bring Your Own Keymodel playground
Source: original entry ↗