Why does Lyro flag a zero credit balance on a key that authenticates fine?

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. Lyro reports the balance itself rather than just the auth result, so the difference shows up before a batch job is started.

Whose rate limits apply when Lyro calls a model through OpenRouter?

The upstream provider's. OpenRouter routes each request to a provider, and rate limits, moderation policies, and context window sizes are set there and differ per model. List Providers and the model endpoint list expose those constraints, so Lyro can route around a provider that is too tight for the job.

Can Lyro actually pay for OpenRouter credits?

It can prepare the payment, not complete it. Create Coinbase Charge returns the calldata needed to fulfil a crypto transaction on the specified blockchain, but signing and submitting that transaction happens outside the toolkit. Lyro sets the top-up up and a person finishes it.

Can Lyro normalise output across different OpenRouter models?

Only through the prompt. Response format varies between models on OpenRouter and the toolkit exposes no normalisation step, so Lyro relies on explicit prompt instructions and on model IDs read from List Available Models rather than fixed IDs that break when the catalog changes.

Openrouter MCP integration

Reads the live model and provider catalog, runs completions, and reports credit balance and key spending before a batch job starts.

Connect Openrouter See all integrations

13actions available

Three actions you can hand over today

Every action runs live through MCP. Nothing to build, nothing to maintain.

Create chat completion
Lyro generates chat responses via OpenRouter, choosing from hundreds of available models. The customer receives a response tailored to quality, speed, or cost preferences.
Get credits
Lyro checks the current API credit balance for the OpenRouter account. The team monitors spend and prepares for top-ups before hitting zero.
List available models
Lyro lists all available models on OpenRouter, including cost and latency specs. The team selects the best model for each conversation based on requirements.

See all 13 actions

How businesses use Openrouter + Lyro

Each card is one request a support team gets, and the Openrouter actions Lyro runs to close it.

Compare live model pricing and context limits
Lyro 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.
List Available ModelsList Model EndpointsList Providers
Run a completion against the model you chose
Lyro 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.
Create Chat CompletionCreate Message (Anthropic Format)Get Generation
Catch a depleted balance before a batch run
Lyro 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.
Get CreditsGet Current KeyGet Models Count
See what stays available under Zero Data Retention
Lyro 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.
List ZDR EndpointsList User ModelsList Embedding Models

How it works

Get started in 3 steps

Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Lyro reads the Openrouter actions it has and picks the ones a request needs.

01
Connect Openrouter
Authorize the Openrouter account your team already uses — one consent screen, no API keys, no mapping tables. Lyro can only do what you granted that account, and you can disconnect it at any time.
02
Tell your agent what you need
Describe the job the way you would hand it to a teammate. Lyro maps it to the Openrouter actions that close it and chains as many as the request needs.
03
Watch it work
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 free

Openrouter · Lyro

Everything else about Openrouter

Setup, permissions, and the limits of what Lyro 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. Lyro reports the balance itself rather than just the auth result, so the difference shows up before a batch job is started.

Every action available in Openrouter

All 13 actions your agent can call on Openrouter, straight from the live MCP connection.

Create chat completion
Generate a chat-style completion.
Create coinbase charge
Create a Coinbase charge for crypto payment to add credits to your OpenRouter account.
Create message (anthropic format)
Create a message using Anthropic Messages API format via OpenRouter.
Get credits
Get the current API credit balance for the authenticated user.
Get current key
Get information about the currently authenticated API key.
Get generation
Retrieve a generation result by its unique ID.
Get models count
Get the total count of available models on OpenRouter.
List available models
List available models via OpenRouter API.
List embedding models
List all available embeddings models via OpenRouter API.
Openrouter list model endpoints
List endpoints for a specific model.
Openrouter list providers
List all AI model providers available through the OpenRouter API.
List user models
List models filtered by user provider preferences, privacy settings, and guardrails.
Openrouter list zdr endpoints
Preview the impact of Zero Data Retention (ZDR) on the available endpoints.