Replicate Model
Run any of the thousands of models available on [Replicate](https://replicate.com/explore). ### How to use 1. Browse the [Replicate model collection](https://replicate.com/explore) and find a model 2. Copy its identifier (shown at the top of the model page) 3. Paste it into this node and click **Load** 4. The node's inputs and outputs update to match the model's parameters ### Model identifier format - \
Inputs
| Name | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | Replicate model identifier in the format provider/model or provider/model:version |
| timeout | number | No | Maximum time to wait for prediction to complete (minutes) |
| poll_interval | number | No | Time between status checks (seconds) |
Reference
External DocumentationRelated Nodes in Artificial Intelligence
Claude Opus 4.1
Most advanced Claude model with latest capabilities
Claude Sonnet 4
Latest Claude Sonnet model with advanced capabilities
Claude 3.7 Sonnet
Mid-tier model between 3.5 and 4.0 generations
GPT-5
Next-generation flagship model
GPT-5 Mini
Faster, cost-effective version of GPT-5
Gemini 2.5 Pro
Most capable model for complex reasoning and creative tasks
Gemini 2.5 Flash
Fast, efficient model for most use cases
Cloudflare Model
Run any model from the Cloudflare Workers AI catalog. A searchable dropdown lists every available model; picking one rebuilds the node's inputs and outputs from its published schema.