Models

Multi-model routing from one API layer

InferGate routes requests through enabled model channels using OpenAI-compatible API patterns. Available models, routing options, prices, limits, and quotas are account-specific and shown in the Dashboard.

Compatibility-first access

Use the /v1/models endpoint to inspect models available to your account, then call /v1/chat/completions with an enabled model name.

Independent gateway

InferGate is an independent API gateway. Provider and model references are for integration compatibility and account-specific routing.

Model availability may change because of upstream availability, account status, payment status, rate limits, provider policy changes, compliance review, or abuse-prevention controls.

Developer use cases

Use model routing to test real product workflows before sending production traffic.

Agent backends

Route tool-using agents through one compatible endpoint while tracking request volume and spend.

SaaS AI features

Prototype assistants, summaries, content tools, and support workflows with dashboard usage visibility.

Model evaluation

Compare enabled routes for latency, output quality, and cost before selecting a production model.

Test model routing with trial credits

New accounts currently include $20 in trial credits. Use the OpenAI-compatible endpoint, create API keys, and review usage in the dashboard before moving to prepaid credits.

OpenAI-compatible endpoint

Use one base URL for compatible requests.

API key management

Create keys for apps, agents, and tools.

Usage dashboard

Watch request and balance activity.

Prepaid credits

Recharge when you are ready to scale.

Model routing

Route enabled models through one gateway.