Supported Models for LLM Gateway

Overview

The LLM Gateway currently supports 100+ models across Anthropic, OpenAI, and open-weight model families, accessed through Anthropic, OpenAI, or Amazon Bedrock. You can configure which of these models are available to your organization — see Model Access Policies for details. The table below is live, fetched directly from the gateway’s public model metadata endpoint. You can query that endpoint yourself for the latest supported models and complete metadata.

Column reference

Column	What it means
ID	The model ID to pass as `model` in a request.
Input Cost ($/MTok)	Cost per million input (prompt) tokens.
Output Cost ($/MTok)	Cost per million output (completion) tokens.
US-only?	Whether every provider that can currently serve this model keeps inference within the United States. See US-only models below.
Chat / Responses / Embeddings / Messages	Which of the gateway’s Supported APIs this model can be called through. A checkmark means the model works on that endpoint today.

US-only models

Most models are available from more than one provider (for example, both Anthropic’s own API and Amazon Bedrock), and Aptible fails over between them automatically — see Provider Failover below. A model is marked US-only only if every provider that could serve it keeps inference within the United States. A small number of models — currently a handful of Claude models plus a couple of open-weight models — are available from at least one provider that doesn’t guarantee US-only processing (for example, a Bedrock global cross-region profile, or the Anthropic direct API for Claude releases before 4.6), so they aren’t marked US-only even though Aptible’s default routing for them may still be a US-pinned provider. If US-only processing is a hard requirement for your workload, check this column before sending PHI or other regulated data to a given model, and contact Aptible Support if you need it enforced rather than just reported.

Provider Failover

When a model is available from more than one provider, the LLM Gateway automatically fails over to another available provider if the primary one has an outage. This happens transparently — you don’t need to configure anything or change your request.

Client-side fallbacks

You can also specify your own fallback models on a per-request basis by including a fallbacks array in your request body, alongside model:

{
  "model": "claude-opus-5",
  "fallbacks": ["gpt-5", "claude-sonnet-5"],
  "messages": [{"role": "user", "content": "..."}]
}

For example, here’s a complete curl request specifying fallback models:

curl https://llm-gateway.aptible.com/openai/v1/chat/completions \
  -H "Authorization: Bearer $LLM_GATEWAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "fallbacks": ["gpt-5", "claude-sonnet-5"],
    "messages": [
      {"role": "user", "content": "Tell me a joke about cloud security"}
    ]
  }'

If the primary model is unavailable, the gateway tries each fallback model in order (each with its own automatic provider failover, per the section above) before returning an error.

Getting Started

Platform

Managed AI

Reference

Supported Models for LLM Gateway

Overview

Column reference

US-only models

Provider Failover

Client-side fallbacks

​Overview

​Column reference

​US-only models

​Provider Failover

​Client-side fallbacks

Overview

Column reference

US-only models

Provider Failover

Client-side fallbacks