nerve
OpenRouter + Nerve
Use any AI model to generate code, text, or images via OpenRouter.ai.
What Nerve can do with OpenRouter
Look things up 7
List Models
List Models. Lists the models available through OpenRouter, with pricing and context limits
List Embedding Models
List Embedding Models. Lists the embedding models available through OpenRouter
List My Available Models
List My Available Models. Lists the models your account can actually use once your provider preferences, privacy settings, and guardrails are applied
List Providers for a Model
List Providers for a Model. Lists every provider serving a specific model, with the pricing and uptime each one offers
List Providers
List Providers. Lists the upstream AI model providers routed through OpenRouter
Get Credits
Get Credits. Gets this account's current API credit balance and total usage
Get API Key Usage
Get API Key Usage. Gets usage, spend limit, and rate-limit info for your connected API key
Make changes 2
Ask LLM
Ask LLM. Ask any model supported by Open Router
Custom API Call
Custom API Call. Make a custom API call to a specific endpoint
Works with
- Agents. An Agent can use OpenRouter when you grant it the capability.
- Workflows. OpenRouter can be a step in a workflow that runs the same way every time.
- Approvals. Actions that matter can wait for a person before OpenRouter is touched.
You connect with: api key.
How it can work
- 1
Something happens
- 2
An Agent or workflow decides what to do
- 3
A person approves, if it matters
- 4
OpenRouter: ask llm
Connected is not unrestricted
Connecting OpenRouter does not give every Agent unrestricted access to it. Each Agent needs the capability granted, the identity it acts as must be allowed, and consequential actions can wait for a person to approve them.
How Nerve controls actionsRelated integrations
- ElevenLabsArtificial intelligenceAI Voice Generator & Text to Speech83 actions
- ZooArtificial intelligenceGenerate and iterate on 3D models from text descriptions using ML endpoints.75 actions
- Mistral AIArtificial intelligenceMistral AI provides state-of-the-art open-weight and hosted language models for text generation, embeddings, and reasoning tasks.46 actions
- Hugging FaceArtificial intelligenceRun inference on 100,000+ open ML models for NLP, vision, and audio tasks
Deploy your first Nerve Agent
Start with one conversation your team handles every day. Give the Agent what it needs to know, connect the tools it should use, and decide where a person steps in.
