Reason over entire datasets. Run on any model. Meter every call to the user who made it.
Early access · provider rates pass through with 0% ModelRelay fee · $1 credit included
One platform · three connected capabilities
Go beyond one prompt.
A reasoning model thinks inside one context window. A Recursive Language Model (RLM) keeps the complete working set in an external environment, then writes code to inspect and reduce it before sending selected slices for model judgment.
Find patterns across years of support tickets, calls, and product events.
Trace behavior across a codebase, logs, incidents, and changing dependencies.
Cross-reference filings, contracts, transcripts, and source material as one investigation.
tokens handled in published RLM evaluations
Same model, run as an RLM: near-zero to 58/100 on questions that require cross-referencing the whole input · OOLONG-Pairs
Evidence for the pattern, not a guarantee for every workload.
Any model. One API.
Weight latency, throughput, cost, and intelligence for your workload—then call any model through the same API.
Compare models on the same controlled task, with output and performance you can inspect.
Set the weights for latency, throughput, cost, and intelligence.
Ship the winner by changing the model string, without rebuilding around another provider.
The model you rank is the model you call. Same request, different string.
curl https://api.modelrelay.ai/api/v1/responses \
-H "Authorization: Bearer $MODELRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5","input":"Hello"}'Change the model. Keep everything else.
Usage in. Revenue out.
Know who made every call, what it cost, and what their plan allows. ModelRelay connects model usage to the end user who initiated it.
Pass the signed-in user so direct calls, root calls, and subcalls resolve to the person who triggered them.
Define plans, model access, credits, and limits without building a second control plane.
Set what customers pay while ModelRelay keeps the underlying model cost attributable.
ModelRelay operates the gateway, RLM runtime, and usage accounting.
Run the data connector and execution environment in your infrastructure.
Model-provider boundary: in either mode, the providers you choose receive the instructions, schema, and selected data needed for their calls.