Model catalog

Supported models and call names

Search the active shared-price catalog and copy the exact value to put in the request model field. Deployment-specific compatible routes are explained below.

The catalog now includes Claude Haiku 5.5 and Gemini 4 Argon alongside GPT-6.1 Sol and Claude Sonnet/Opus 5.5. Availability depends on your connected accounts; check GET /v1/models before calling.

Haiku 5.5 uses the short-context token tariff (prompts up to 100k tokens). Argon uses introductory rates through November 30, 2026. Long-context, cache-write and tool surcharges are not separately billed by the current token tariff.

Shared priced models

Priced providers

DeepSeek and Ollama support

The priced catalog and the runtime model directory have different scopes.

Shared compatible upstream

DeepSeek

Built-in call names

deepseek-v4-flashdeepseek-v4-pro

These models appear in the table when DeepSeek routing and pricing are enabled for this deployment.

Local compatible upstream

Ollama

Deployment-specific call names

Models are discovered from the connected Ollama server and exposed through the configured alias. Because every installation can have different models, there is no fixed global Ollama model list or price.

Use the authenticated runtime model endpoint as the source of truth:GET /v1/modelsThe table below only lists models with active shared sell-side pricing.

Active shared-price models

Loading model catalog...