POST /accounts/{account_id}/ai/run
Execute an AI model by specifying the model name in the request body.
This endpoint provides a generic interface for running AI models where the model name is part of the request payload rather than the URL path. It supports all AI Gateway features including caching, custom headers, and request options.
Model-specific inputs available in Cloudflare Docs.
Servers
- https://api.cloudflare.com/client/v4
Path parameters
| Name | Type | Required | Description |
|---|---|---|---|
account_id |
String | Yes |
Request headers
| Name | Type | Required | Description |
|---|---|---|---|
Content-Type |
String | Yes |
The media type of the request body.
Default value: "application/json" |
Request body fields
| Name | Type | Required | Description |
|---|---|---|---|
input |
Object | Yes |
Model-specific input data. Format varies by model type. |
options |
Object | No | |
options.gateway |
Object | No | |
options.gateway.id |
String | No |
AI Gateway ID for caching and logging |
options.gateway.cacheTtl |
Number | No |
Cache TTL in seconds |
options.gateway.skipCache |
Boolean | No |
Skip cache lookup for this request |
options.extraHeaders |
Object | No |
Additional headers to pass to the AI provider |
model |
String | Yes |
The AI model to execute (e.g., openai/gpt-5.5, anthropic/claude-opus-4.7) |
How to start integrating
- Add HTTP Task to your workflow definition.
- Search for the API you want to integrate with and click on the name.
- This loads the API reference documentation and prepares the Http request settings.
- Click Test request to test run your request to the API and see the API's response.