INTELLIGENCE FOR YOUR NEXT REQUEST

Choose where intelligence runs.

Connect your own provider credits for more hosted models, try the free preview, or keep inference on your device with browser models.

NEW / CONNECTED INFERENCE

Your models.
Your balance.

Connect OpenRouter and run hosted models here using your own credits. No crypto wallet required.

Connect your account
Add credit with the provider
Choose a model and run

Ready when you are

You pay OpenRouter directly. Agentport does not collect or hold your credit.

Add credits on OpenRouter ↗Manage limits or revoke access ↗

Can I use my X Money card?

OpenRouter accepts major cards. Eligible X Money users can try their Visa card at that checkout. Acceptance depends on the issuer and processor and has not been tested by Agentport. This is not a direct X Money integration.

Choose your intelligence

Loading catalog…

RESPONSE

Connect your account, choose a model, and make your first request.

Requests go directly from your browser to OpenRouter and its model providers. Your key is stored in this tab’s session storage; prompts and responses are not saved by this panel. Disconnect clears the local key; revoke it at OpenRouter to end its access.

AGENTPORT COMPUTE ROUTER / BETA

Describe the compute. Compare the routes.

Need Solana USDC payments or a raw GPU? Open compute workspace ↗

Find hosted inference by model, context, and budget. Review a provider, then run with your connected OpenRouter credits.

Request requirementsModel

Context capacity (tokens)Max output tokensRequest budget (USD)Observed latency filterRank by

Region: any (provider location is not verified). Latency is historical, not a response-time guarantee. Unknown latency is excluded when a filter is set.

Cost review uses the full context input allowance plus maximum output, at catalog prices. It is not an exact token quote or account spending cap; provider and account fees may apply. Set a key limit on OpenRouter. Routes expire after 60 seconds; no automatic fallback or paid retry.

Your compute request

Connect OpenRouter above to run. Comparisons are free.

Agent discovery API: POST /api/compute. Read the request format ↗

Try a request

No key. No wallet.

MODEL RESPONSE

Your response appears here. Choose an example or write your own prompt to begin.

Shared preview capacity · 6 requests/minute per instance/IP · No prompts or outputs are saved by Agentport. Requests run on the server.

BUILT FOR INTEGRATION

One familiar interface.

Use the chat-completions request format with your existing tooling. A small API with live streaming with clear limits and no API key.

POST · Chat completions: /v1/chat/completions
GET · Model catalog: /v1/models
Model identifier: toll-small-135m

MORE MODELS. YOUR COMPUTE.

A bigger model, right here.

Download once, run on your device. No API key or paid inference account. Prompts stay in this tab; model files download from their public repository.

WebGPU required

Larger downloads and GPU memory are required. Performance depends on the device. These models run in the browser, not through the hosted chat API; no paid fallback is used.