Marketplace
Browse and deploy AI models and providers — real pricing and live availability.
Marketplace
Browse every model and provider available on Hanzo Cloud, compare real per-token pricing, and deploy one into your app in a click. The Marketplace is a storefront over the live model catalog — no fabricated listings, no stale prices.
Browse the Catalog
Open Apps → Marketplace in the console to browse by category (chat, embeddings, vision, audio, rerank), filter by provider, and see live availability. Each listing shows the model's context window and its real input/output price per million tokens. "Try it" opens the Playground with the model preloaded.
Catalog API
The storefront is backed by the pricing catalog, which you can query directly:
curl https://api.hanzo.ai/v1/pricing/models \
-H "Authorization: Bearer hk-..."{
"models": [
{
"id": "claude-sonnet-4-5-20250929",
"name": "Claude Sonnet 4.5",
"provider": "anthropic",
"context": 200000,
"input_per_mtok": 3.00,
"output_per_mtok": 15.00
}
]
}Prices are the real per-million-token rates; a model with no published price renders as — in the console rather than a guess.
Deploy a Model
Once you have picked a model, call it through the OpenAI-compatible LLM Gateway with the same hk- key:
curl https://api.hanzo.ai/v1/chat/completions \
-H "Authorization: Bearer hk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-sonnet-4-5-20250929",
"messages": [{"role": "user", "content": "Hi"}]
}'Related
- LLM Gateway — call any model in the catalog
- AI Studio — compose catalog models into apps
- GPUs · API Keys · API Reference
How is this guide?
Last updated on
Hanzo Embeddings
Generate, store, and search vector embeddings at scale — an OpenAI-compatible embeddings API on the Hanzo gateway that pairs with Vector.
Hanzo SQL
Managed PostgreSQL — provision databases, create copy-on-write branches, and scale reads with replicas over a single API and the standard Postgres wire protocol.