Skip to main content
Last Updated: October 19, 2026
Salad AI Gateway is currently in beta. Pay-per-token access is self-service.

What is Salad AI Gateway?

Salad AI Gateway is a managed LLM API service that gives you direct access to powerful open-source models through a single, OpenAI-compatible endpoint - with no infrastructure to deploy or manage. It is powered by SaladCloud’s distributed GPU network, bringing the same cost-efficiency of self-hosted models with the simplicity of a hosted API. Any tool or library that supports a custom base URL - Aider, OpenCode, OpenClaw, Cline, Cursor, Goose, Vercel AI SDK, and more - works with Salad AI Gateway out of the box.

API Endpoint

Available Models

The following models are currently available: Additional models will be added as the service moves toward general availability.

Access Model

Access is self-service and billed per token. Each AI Gateway key belongs to one user and one organization, and requests are billed to that organization’s credits; a positive balance is required to admit new requests.

Billing

Pay-per-token requests use the published input and output token rates, with no concurrency limit. Usage draws from the credit balance of the organization associated with your key. Requests already admitted complete and are billed even if credits run out during generation or the key is revoked or regenerated. Follow Pay-Per-Token Onboarding to add credits and create your AI Gateway API key.

Quick Start

The API follows the OpenAI v1/chat/completions format. Send requests using your organization-specific AI Gateway API key in the Authorization header. This is not the account API key used with Salad-Api-Key:
Replace <your-ai-gateway-api-key> with the key created for the organization you want to bill.

Use with OpenAI-Compatible Tools

Because Salad AI Gateway exposes a standard OpenAI-compatible endpoint, you can use it with any tool that supports a custom base URL. We have integration guides for many popular agentic tools - Cline, Aider, OpenCode, OpenClaw, Kilo Code, Roo Code, Continue, Goose, Hermes Agent, and more. In guides with both backends, follow the Salad AI Gateway tab. Self-hosted Container Engine deployments use different endpoints and authentication. For AI Gateway, set your organization-specific AI Gateway key in the tool’s API key field (sent as Authorization: Bearer) and point the base URL to https://ai.salad.cloud/v1. Do not add a Salad-Api-Key custom header.

Cline

VS Code AI coding agent

Aider

CLI AI pair programmer

OpenCode

Terminal coding agent

OpenClaw

Always-on AI assistant

Kilo Code

VS Code coding agent

Roo Code

VS Code AI coding agent

Continue

VS Code + JetBrains coding assistant

Vercel AI SDK

TypeScript AI app framework

Goose

CLI + desktop AI agent

Hermes Agent

Self-improving AI agent with MCP
Python (openai SDK):
Environment variables (for tools like Aider, etc.):
These tool-specific variables contain the same AI Gateway key set in Quick Start, not an account API key or an OpenAI API key.

Why Salad AI Gateway?

  • No Infrastructure - no container groups to deploy, no replicas to manage, no cold starts to worry about
  • Always on - our distributed GPU network ensures high availability and reliability
  • OpenAI-compatible - easy integration with any OpenAI-compatible tool
  • SaladCloud Pricing - 90% cost savings vs traditional providers
  • Data Privacy - your data is never used for training
  • Powered by Sustainable Computing - utilizing otherwise wasted GPU resources to reduce carbon footprint

Get Access

Pay-per-token access is available through self-service onboarding. Self-onboard for pay-per-token access or learn more about Salad AI Gateway. Already have a key? See Manage Your AI Gateway API Key for rotation and deletion, or Errors for billing and access failures.