One API for leading AI models. With a budget for every agent.
Cedra is building a model router like the ones you already use, with a separate key and spending limit for each agent, so one agent cannot drain the balance the others depend on.
| Agent | Key | Limit / day | Spent today | Status |
|---|---|---|---|---|
| research-agent | ck_…7f2 | $50.00 | $12.40 | Running |
| support-agent | ck_…a91 | $20.00 | $18.90 | Near limit |
| nightly-loop | ck_…3c0 | $5.00 | $5.00 | Paused |
research-agent → provider-a/model-x failed → fallback provider-b/model-x OK
Who Cedra is for
Designed for agents that run all night.
Agents call models thousands of times, hit provider failures and spend real money while nobody is watching. We are designing the router around that.
-
A key and a limit per agent
PlannedEach agent will get its own key and spending limit, so one runaway loop cannot drain the budget.
-
One balance, protected
PlannedYou will top up one balance and pay per request from it. Each agent's limit keeps one runaway agent from using up the balance the rest of your agents need.
-
Many models, one API
In developmentFrontier and open-source models behind one API. Our goal: every model served directly by its provider, not a reseller, with the option to pin a provider so a model behaves consistently from call to call.
-
Fallback when a provider fails
PlannedWhen a provider fails, requests will switch over automatically, so your agent does not stop halfway through a task.
Get an early key. We invite in waves.
The router is in development. We will let developers in by waves, as many as we can onboard by hand. Tell us what hurts most and we will use it to decide who goes first.
- An API key before public launch
- Beta access to per-agent keys and spending limits as they ship
- A say in which models and providers we add first
What happens after you sign up. We read your answers and place you in a wave. When your wave opens, you will get an email with your key and a quickstart. Waves are small on purpose, so each group gets real attention from the team. We do not have wave dates yet.
What Cedra is, in four answers.
What is Cedra?
Cedra is a Move L1 blockchain with a built-in indexer, oracle and cross-chain messaging. The Cedra team is building a model router on top of it: one API for frontier and open-source models, with a separate key and spending limit for each AI agent. The router is in development.
Is the Cedra model router available today?
Not yet. The router is in development. Developers can join the early access list and will get a key when their wave opens. The Cedra L1, its indexer and its randomness oracle are available today.
How will per-agent spending limits work?
You will top up one balance and pay per request from it. Each agent will get its own API key and spending limit, so one agent stuck in a loop cannot use up the balance your other agents need.
Do I need to use a blockchain to use the router?
No. If you only need models, you will use Cedra like any model API. Chain data, randomness and cross-chain messaging will be there when an agent needs them.
Why there is a chain underneath.
You will not need to touch a blockchain to use the router. The chain is there for agents that need chain data, randomness or messages to other chains, without adding vendors.
- Designed throughput
- 10k+TPS
- Designed finality
- <1s
- Built into the network
- Indexer, oracle, messaging
Design targets from the Cedra architecture docs. Move VM with Block-STM parallel execution. Cedra for Move builders →
