Generate a response (BYOK)
Use Claude with your own API key to generate human-like responses to a given prompt or question. Maximum response length varies by model. Accepted file formats: PNG, JPEG, WEBP, GIF and PDF. To stay under the 32 MB request limit for both the prompt and files, please compress large PDFs.
This Wrk Action uses AI-generated content. Like all AI content, use with caution; information may be outdated, incomplete, or inaccurate.
Application
- Anthropic
Inputs (what you have)
| Name | Description | Data Type | Required? | Example |
|---|---|---|---|---|
| Connected Account | The Connected Account with your Anthropic API key | Connected Account | Yes | |
| Prompt | The prompt to generate completions for. Input will be truncated if it exceeds the limit set by the API | Text (Long) | Yes | |
| Model | The Claude model to use. Options: Claude Opus 5.5, Claude Fable 5.1, Claude Sonnet 5 | Predefined Choice List | Yes | |
| System message | The message which sets the context and expectations for a conversation with the AI | Text (Long) | No | |
| File input 1 | The file to be provided to the AI | File | No | |
| File input 2 | A second file to be provided to the AI | File | No | |
| File input 3 | A third file to be provided to the AI | File | No | |
| Reasoning effort | Constrains effort on thinking for thinking models. Reducing reasoning effort can result in faster responses and fewer tokens used on thinking. Leave blank to use the model default. Options: Low, Medium, High, Extra high, Max | Predefined Choice List | No | |
| Return response as JSON? | If set to true, the response of the AI will return valid JSON | True/False | No | |
| Structured output schema | JSON Schema to enforce structured output. When provided, Claude will guarantee the response conforms to this schema. Shown when Return response as JSON? is true | Text (Long) | No |
Outputs (what you get)
| Name | Description | Data Type | Required? | Example |
|---|---|---|---|---|
| Generated text | Text content created by artificial intelligence | Text (Long) | No | |
| Stop reason | The reason the response was stopped | Text (Short) | No |
Outcomes
| Name | Description |
|---|---|
| Success | This status is selected if the job has successfully completed. |
Requirements
- An Anthropic Connected Account with a valid Anthropic API key
- Access to the selected Claude model on your Anthropic account