Resources

Models & Catalog Reference

Discover available text-to-image, image-to-image, text-to-video, and image-to-video models using E2X 3-part slugs, public catalog endpoints, and machine-readable llms.txt schemas.

Catalog Discovery Endpoints

Explore the interactive E2X Model Catalog or query public catalog routes programmatically without an API key to inspect model input schemas, enums, defaults, and dynamic pricing multipliers:

GET/v1/catalog/models?category=text-to-image&provider=google&limit=20
Unauthenticated Public

Lists active catalog models with optional category, provider, search, featured, and pagination parameters.

GET/v1/catalog/models/:provider/:model/:capability
Unauthenticated Public

Returns the full specification, inputSchema, outputSchema, and pricing factors for a 3-part model slug.

GET/v1/catalog/providers
Unauthenticated Public

Lists active model providers (Google, OpenAI, ByteDance) and model counts.

GET/v1/catalog/categories
Unauthenticated Public

Lists active generation capabilities such as text-to-image, image-to-image, text-to-video, and image-to-video.

GET/v1/models
Bearer Token Required

Authenticated model listing requiring the list_models operation scope.

GET/v1/providers
Bearer Token Required

Authenticated provider listing requiring list_models; pair with GET /v1/providers/:providerId/models.

cURLFetch Schema & Pricing for Nano Banana 2.1
curl -s "https://api.e2x.ai/v1/catalog/models/google/nano-banana-2.1/text-to-image" | jq '.data'

Representative Models in Production

Every production request uses a 3-part slug (<provider>/<model>/<capability>):

Model SlugProviderCapabilityBase Cost
google/nano-banana-2.1/text-to-imageGoogletext-to-image60,000 µ¢ ($0.06) / request
google/nano-banana-2-lite/text-to-imageGoogletext-to-image34,000 µ¢ ($0.034) / request
openai/gpt-image-2.6-sunburst/text-to-imageOpenAItext-to-image30,000 µ¢ ($0.03) / request
openai/gpt-image-2.6-sunburst/edit-imageOpenAIimage-to-image30,000 µ¢ ($0.03) / request
google/veo-3.1-fast/text-to-videoGoogletext-to-video100,000 µ¢ ($0.10) / second
google/veo-3.1-fast/image-to-videoGoogleimage-to-video100,000 µ¢ ($0.10) / second
bytedance/seedance-2.0-mini/text-to-videoByteDancetext-to-video60,000 µ¢ ($0.06) / second
bytedance/seedance-2.0-mini/image-to-videoByteDanceimage-to-video60,000 µ¢ ($0.06) / second

Machine-Readable llms.txt Specs

LLM coding agents and code generators can fetch plain-text parameter schemas directly from /llms.txt, /llms-full.txt, or per-model at /files/llms/models/<provider>/<model>/<capability>/llms.txt.

Dedicated Model & Capability API Hubs