ai-gateway inkling model-routing reasoning cost-tracking

Inkling model now available on AI Gateway

Thinking Machines' broad generalist model with controllable reasoning effort is now accessible via Vercel's unified API layer with native streaming support.

Summary

Consolidates model access, cost tracking, and failover logic in a single endpoint; eliminates per-provider API management and reduces operational overhead for multi-model deployments.

Why it matters

Consolidates model access, cost tracking, and failover logic in a single endpoint; eliminates per-provider API management and reduces operational overhead for multi-model deployments.

Implementation verdict

Replaces direct provider integrations for teams already using AI Gateway; requires one-line model string change in AI SDK. Worth trying now if you're evaluating reasoning models—no lock-in risk since Gateway abstracts provider changes.

Sources

1.Inkling is a broad generalist model, trained across agentic, reasoning, coding, instruction-following, factuality, vision, and audio tasks
2.The model also supports controllable thinking effort
3.AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference
4.set `model` to `thinkingmachines/inkling`

Dev Signal

Get briefs like this in your inbox — free, every weekday.

100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.

Read the full issue →All briefs