Pricing
Understand the costs of running AI coding agents on Superconductor.
When using AI coding agents, there are two things to pay for: tokens and compute.
Tokens
Tokens are the currency of large language models. Every time an agent reads code, thinks about a problem, or generates a response, it consumes tokens.
Currently, you must pay for your own tokens by providing your own API keys from LLM providers. See Credentials for details.
Compute
Compute refers to the cloud infrastructure where your agents run. Each implementation spins up an isolated environment with CPU, memory, and storage to execute agent tasks.
We plan to charge for compute on a plan basis, such as:
- Up to N hours of compute per month
- Up to K parallel agents running simultaneously
- Additional usage billed separately
Current pricing
While we are finalizing our pricing model, Superconductor is free to use. You only need to provide your own LLM API keys or connect your existing AI subscriptions.
We'll announce our compute pricing before any charges take effect, giving you time to understand costs and adjust your usage.