Connect Replicate to your AI agent
Replicate allows users to run AI models via a cloud API without managing infrastructure.
We set up the connection using your own Replicate account, with keys you control, and keep it running. Your agent picks it up and starts doing the work.
Actions
What your agent can do in Replicate
Each one is a real action the agent can take on its own, the same things a person clicking around Replicate could do. Read-only by default; write actions are confirmed against your policy.
- Get Account Information Tool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
- Cancel Prediction Tool to cancel a prediction that is still running. Use when you need to stop an in-progress prediction to free up resources or halt execution.
- Get model collection Tool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
- List model collections Tool to list all collections of models. Use when you need to retrieve available model collections. Collections are curated groupings of related models. Response includes only collection metadata (name, slug, description…
- Create Model Tool to create a new Replicate model with specified owner, name, visibility, and hardware. Use when you need to create a destination model before launching LoRA/fine-tune training.
- Create Prediction Tool to create a prediction for a Replicate Deployment. IMPORTANT: This action ONLY works with Replicate Deployments (persistent instances you create and manage), NOT public models. Deployments are created via REPLICATE…
- Create Deployment Tool to create a new deployment with specified model, version, hardware, and scaling parameters. Use when you need to deploy a model for production use with auto-scaling.
- Delete Deployment Tool to delete a deployment from your account. Use when you need to remove a deployment. Deployments must be offline and unused for at least 15 minutes before deletion.
- Get Deployment Details Tool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings.
- List deployments Tool to list all deployments associated with the account. Use when you need to retrieve deployment configurations and their latest releases.
- Create File Tool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata.
- Delete File Tool to delete a file by its ID. Use when you need to remove a file from storage. Returns 204 No Content on success.
- Get File Details Tool to get details of a file by its ID. Use when you need to inspect uploaded file information before further operations. Returned URLs may be short-lived; download or persist needed files promptly after retrieval.
- List Files Tool to retrieve a paginated list of uploaded files. Use to view all files created by the authenticated user or organization. Files are sorted with most recent first. Pagination is cursor-based: follow the next cursor u…
- Get Prediction Tool to get the status and output of a prediction by its ID. Use when you need to check on a running prediction or retrieve the results of a completed prediction.
- List Available Hardware Tool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform.
- List model examples Tool to list example predictions for a specific model. Use when you want to retrieve author-provided illustrative examples after identifying the model. Returned examples are minimal working payloads; cross-reference wit…
- Get Model Details Tool to get details of a specific model by owner and name. Consult the returned input schema before constructing any prediction request — each model defines its own required/optional fields (e.g., `prompt`, `aspect_rati…
- List Public Models Tool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date.
- Create Model Prediction Tool to create a prediction using an official Replicate model. Use when you need to run inference with a specific model using its owner and name. Supports synchronous waiting (up to 60 seconds) and webhooks for async no…
- Get Model README Tool to get the README content for a model in Markdown format. Consult alongside REPLICATE_MODELS_EXAMPLES_LIST before calling REPLICATE_CREATE_PREDICTION — Replicate enforces strict JSON schemas on model inputs and ret…
- Get Model Version Tool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata.
- List Model Versions Tool to list all versions of a specific model. Use when you need to see all available versions of a model, sorted by newest first.
- Create Prediction Tool to create a prediction to run a model by version ID. Use when you have a specific model version identifier and need to run inference with provided inputs. Supports synchronous waiting and webhook notifications.
- List All Predictions Tool to list all predictions for the authenticated user or organization with pagination. Use when you need to retrieve prediction history or filter predictions by creation date.
- Search Models and Collections Tool to search for models, collections, and docs using text queries (beta). Use when you need to find relevant models or collections based on keywords or descriptions.
- Cancel Training Tool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
- Create Training Job Tool to create a training job for a specific model version. Use when you need to fine-tune a model with custom training data. Supports webhook notifications for training status updates.
- List Training Jobs Tool to list all training jobs for the authenticated user or organization with pagination. Use when you need to retrieve training history or check the status of training jobs.
- Update Model Metadata Tool to update metadata for a model including description, URLs, and README. Use when you need to modify a model's visibility, documentation, or associated links.
- Get Webhook Signing Secret Tool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity.
Setup
How we connect it
- 1
Connect your account
You create a key in Replicate, a key you create and control, and paste it in once. It lives in a secrets store on your server, not with us.
- 2
Set the guardrails
Read-only by default. You choose which write actions the agent may take, and anything outside that policy gets confirmed with you first.
- 3
We keep it running
Health checks on every connection, updates handled for you, and we watch the first week of activity to make sure the work lands.
FAQ
Replicate questions, answered.
With a key you create and control. You paste it in once, it is stored in a secrets store on your server, permissions are scoped to the minimum the agent needs, and you can revoke it at any time.
The actions Replicate's API allows, the same things a person clicking around the app could do. Connections start read-only by default; write actions are confirmed against the policy you set before the agent takes them.
Connections are priced per tool on top of the base plan. Some are included, some are premium. See pricing for how connection charges work.
Standard tools are ready inside 7 business days of the setup call. We test the connection end to end, walk you through how the agent uses it, and watch the first week of activity.
Ready to put Replicate to work?
Tell us what your team runs on. We set up the connection, secure it, and your agent takes it from there.
All product names, logos, and brands are property of their respective owners; used for identification only. ZeroToClaw is not affiliated with or endorsed by Replicate.