Model gateway
Expose AI models through a unified router so applications can connect to model providers through one gateway instead of wiring each integration separately.
InsForge is an agent-native cloud infrastructure platform for production apps with AI coding agents, featuring model gateway, compute, database, auth, storage and hosting.
InsForge is an agent-native cloud infrastructure platform for building and running production apps with AI coding agents. The site positions it as a backend and infrastructure layer that can be operated end to end through CLI and skills, rather than by manually assembling separate cloud services.
The platform combines a model gateway, compute, deployment, database, authentication, storage, hosting, and other application services in one place. Its pricing page separates subscription plans from compute usage, and its changelog shows ongoing updates across edge functions, payments, model routing, sites, and workflow tooling.
Expose AI models through a unified router so applications can connect to model providers through one gateway instead of wiring each integration separately.
Provision per-project backend infrastructure that includes an API server and Postgres database, with compute billed separately from the main subscription.
Deploy backend logic as edge functions and host frontend sites with live URLs, production domains, environment variables, and deployment logs.
Add authentication, cloud storage, realtime data updates, cron jobs, analytics, payments, and messaging from the same platform.
Run your own containers and long-running workloads through Custom Compute when the default project backend is not enough.
Use a CLI- and skills-based workflow intended for AI coding agents rather than manual dashboard-only operation.
Use the platform when you want an agent to assemble backend services without switching between separate vendors for auth, storage, database, and deployment.
Use the model gateway and related AI services when your product needs access to models through a single routing layer instead of direct provider-specific integration work.
Use edge functions, sites, cron jobs, and realtime updates when you need an application backend that handles both scheduled logic and live user-facing experiences.
Use Custom Compute when your project needs containers or long-running workloads that are distinct from the default per-project backend server.
Use the pricing structure when you want to estimate production costs by separating subscription fees from compute usage and choosing instance sizes per project.
InsForge is an agent-native cloud infrastructure platform. It provides services such as a model gateway, database, authentication, storage, edge functions, and hosting, with workflows designed for coding agents to operate through CLI and skills.
The homepage says InsForge is built for AI coding agents and for teams that want to go from idea to production without configuring infrastructure by hand. The pricing page also distinguishes it from traditional cloud billing by separating subscription plans from compute usage.
The site points users to `https://insforge.dev/skill.md` as the canonical setup workflow. It states that this workflow supersedes guesses about the CLI, signup, or API.
The pricing page shows a Free plan, a Pro plan, and an Enterprise option. Free is aimed at prototypes, demos, and side projects, while Pro is aimed at production apps and Enterprise adds security and compliance-oriented options such as SSO and SOC2.
The changelog shows product updates for services such as edge functions, payments, model gateway, sites, and contributor workflows. This suggests the platform is actively evolving, but the site does not provide a single published compatibility matrix on the pages reviewed.
Traffic data is for reference only.
| Apr | 146257 |
|---|---|
| May | 190477 |
| Jun | 159102 |