Introduction

A quick orientation to The Grid: what it does, what you get out of it, and how it fits into your stack.

The Grid is a Spot Market for AI Inference

You pick a task type. Then you pick a quality tier. We route your request to a qualifying supplier at the lowest live price for that combination.

Task types describe the workload:

• Text for general-purpose chat and reasoning.

• Code for code generation, editing, and review.

• Agent for tool use, function calling, and multi-step workflows.

Quality tiers describe how strong the underlying model has to be:

• Standard for everyday tasks where speed and cost matter most.

• Prime for production workloads that need consistent, capable output.

• Max for the hardest tasks where you want frontier-class quality.

Each task type and tier maps to an instrument, a published spec like text-prime or code-max. Suppliers compete on every order. Any model that drifts below spec is removed from the eligible set, so you get the price of competition without giving up the quality bar.

We're compatible with both OpenAI Chat Completions and Anthropic Messages formats. See the API reference for base URLs, auth headers, and request shape.

What this means for you

• Lower price for the quality you need. Suppliers bid against each other on your order. Pricing tracks live supply and demand, not a published rate card.

• One API, no SDK rewrite. Keep your OpenAI or Anthropic client. Swap in an instrument string as the model name and ship.

• No vendor lock-in. You aren't tied to one model house. If a better-priced model qualifies, we route to it without you changing code.

Where to go next

• Quickstart: make your first call in under five minutes.

• Choose an instrument: pick the task type and quality tier for your workload.

• Current instruments: see the live specs and what each one is benchmarked against.

• Benefits: what you gain by consuming inference at market prices.