Four new models routed through Relay, with context, pricing, and where to start.
Norvane Norvane

Four new models on Relay this week.

Four models joined the Relay catalog this week. Every one is reachable with your existing API key and the same completions endpoint.

halcyon/tessera-3

Provider: Halcyon Systems

Context: 256K

Price per million tokens: $0.40 input / $1.60 output

A general-purpose reasoning model tuned for long agentic tool loops.

View model →
 

brightwater/marlin-vision

Provider: Brightwater AI

Context: 128K

Price per million tokens: $0.15 input / $0.60 output

Image and PDF understanding at a price that suits batch document pipelines.

View model →
 

orrin/embed-large-v2

Provider: Orrin Labs

Context: 8K

Price per million tokens: $0.02 input

A 1,536-dimension embedding model for retrieval, semantic search, and classification, with text and image inputs.

View model →
 

sundial/echo-mini

Provider: Sundial

Context: 64K

Price per million tokens: $0.05 input / $0.20 output

A fast small model for classification, routing, and structured extraction.

View model →

Route to any of them

  1. Create an API key.
  2. Put the model id in the model field of a request; the quickstart has curl and SDK examples.
  3. Add credits to unlock every model in the catalog.
Browse the full catalog

Try any model in the playground before writing code.

The Norvane Relay Team.

Norvane Labs, 880 Kestrel Way, San Francisco, CA 94107
Norvane © 2024–2026
Privacy  ·  Terms  ·  Unsubscribe