An illustrated infrastructure interchange joining different technology connections through one governed route

Provider compatibility

One API. The model market behind it.

Change providers in configuration, not throughout your product. Route across hosted, cloud, and local models with provider fallback, key rotation, load balancing, semantic caching, rate limits, and unified telemetry.

Explore every model How the gateway works

0122 providers
02One catalog
03One API

Compatibility directory

Pick what you already use.

Every entry leads to its exact model catalog, setup guide, or a transparent explanation of the connection path.

OpenAI

Native provider

Route GPT, reasoning, embedding, image, speech, and moderation models through one catalog.

OpenAI models

Anthropic

Native provider

Use Claude models with the same routing, fallback, cost, and trace controls as every provider.

Anthropic models

Google Gemini

Native provider

Connect Gemini models directly or through Vertex AI while keeping one application interface.

Gemini models

Mistral

Native provider

Route Mistral's general, coding, and embedding models from the shared gateway surface.

Mistral models

Ollama

Local provider

Bring local models into the same routing and observability plane as hosted inference.

Ollama models

Groq

Native provider

Use low-latency Groq inference as a primary route or fallback without changing clients.

Groq models

Azure OpenAI

Cloud provider

Connect Azure-hosted OpenAI deployments through Everstack's unified routing layer.

Azure OpenAI models

AWS Bedrock

Cloud provider

Reach Bedrock-hosted model families while preserving consistent request and trace semantics.

Bedrock models

DeepSeek

Native provider

Add DeepSeek chat and reasoning models to routes, fallbacks, and cost policies.

DeepSeek models

Qwen

Native provider

Use Qwen model families through the same OpenAI-compatible application endpoint.

Qwen models

Connection model

One clean path into production.

Connect provider keys

Define the route

Choose primary models, fallback chains, load-balancing policy, cache behavior, and limits.

Call one API

Applications use a stable gateway contract while Everstack handles provider-specific behavior.

Explore the full surface

Compatibility works across the stack.

View compatibility overview

Languages & SDKs Agent Frameworks Model Providers Tools & Integrations

Build without lock-in

Bring your stack. Operate it as one.

Start with the gateway, then add the runtime services your application needs without replacing the tools it already uses.

Start with $5 credits