Reads the live model and provider catalog, runs completions, and reports credit balance and key spending before a batch job starts.
13actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro generates chat responses via OpenRouter, choosing from hundreds of available models. The customer receives a response tailored to quality, speed, or cost preferences.
Ayro checks the current API credit balance for the OpenRouter account. The team monitors spend and prepares for top-ups before hitting zero.
Ayro lists all available models on OpenRouter, including cost and latency specs. The team selects the best model for each conversation based on requirements.
Each card is one request a support team gets, and the Openrouter actions Ayro runs to close it.
Ayro pulls the current model catalog and the endpoints behind a specific model, so a decision about cost or context window is made against what OpenRouter offers today rather than an ID copied months ago.
Ayro sends the assembled messages in either the OpenAI-style or Anthropic-style format and then fetches the generation record, so token counts, cost, and latency are known for that specific call.
Ayro checks the credit balance and the usage and spending limits on the active key, so a long job is not launched against an account that will start failing partway through.
Ayro previews which endpoints remain reachable once ZDR is enabled and lists the models your provider preferences, privacy settings, and guardrails already allow, so a policy constraint surfaces before it blocks a request.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Openrouter actions it has and picks the ones a request needs.
Authorize the Openrouter account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Openrouter actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeOpenrouter · Ayro
What can you do in Openrouter without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Openrouter.
Because the two are not the same signal. Get Credits can return total_credits=0 on a key that authenticates correctly, which looks healthy but will fail every paid model generation. Ayro reports the balance itself rather than just the auth result, so the difference shows up before a batch job is started.
All 13 actions your agent can call on Openrouter, straight from the live MCP connection.
Generate a chat-style completion.
Create a Coinbase charge for crypto payment to add credits to your OpenRouter account.
Create a message using Anthropic Messages API format via OpenRouter.
Get the current API credit balance for the authenticated user.
Get information about the currently authenticated API key.
Retrieve a generation result by its unique ID.
Get the total count of available models on OpenRouter.
List available models via OpenRouter API.
List all available embeddings models via OpenRouter API.
List endpoints for a specific model.
List all AI model providers available through the OpenRouter API.
List models filtered by user provider preferences, privacy settings, and guardrails.
Preview the impact of Zero Data Retention (ZDR) on the available endpoints.
Same connection, same setup. Pick the next one your team already uses.
Inventories models, clusters, and anomaly detectors, reads their evaluations and predictions, and sets up projects and external data connectors.
Sends prompts to deepseek-chat or deepseek-reasoner with tool calling and thinking mode, and checks balance and model availability first.
Creates a project, reports on its experiments and session history, and deletes the project when the work behind it is finished.
Searches your document collections and returns ranked passages with sources, uploads new files, retires stale ones, and syncs local connectors.
Creates image, video, LiDAR, and text annotation tasks, batches and finalizes them, reports completion counts, and reassigns Studio projects.
Submits a prompt as a Veo generation job, tracks the operation until it finishes, and downloads the finished clip.

Authorize the account and your agent has all 13 actions from the first conversation.
