Multimodal AI Gateway
Unified multimodal generation and embedding gateway
Map text generation and embeddings to configurable providers/models with hooks, error normalization, and multimodal support.
Capabilities
- ✓Logical routing: visual generation and embedding setup
- ✓Text, JSON, inline media, and file upload generation
- ✓Multimodal embeddings (text + image)
- ✓Multi-model routing with unified configuration
- ✓Built-in observability across the request lifecycle
Example flow (same canvas as the console)
Static illustration below—pan and zoom like the console route editor (drag background, scroll to zoom).
Demo route id: chat · conditions are examples; configure real logic in the console
Start
chat
Access protocols (enabled on the Gateway detail page); each path runs the same logical route flow below
Entry
Google Gen AI SDK
v1beta/**
baseUrl without /v1beta
Entry
OpenAI · Chat
v1/chat/completions
baseURL includes /v1
Entry
OpenAI · Responses
v1/responses
baseURL includes /v1
if/else
input format = image+text
Endpoint
Endpoint · Gemini 2.0 Flash
if/else
metadata.tier = pro
Endpoint
Endpoint · GPT-4o
ELSE → Fallback
Fallback
model from request · resolved at endpoint
API prefix
/g/{public-id}