Productsup

Use Claude with the data service Custom Prompt With Dynamic Values

Point the Custom Prompt With Dynamic Values data service at Anthropic's Claude models by changing three connection settings, and learn which limitations apply.

The Custom Prompt With Dynamic Values data service connects to an OpenAI-compatible AI tool. Anthropic offers an OpenAI-compatible endpoint for its Claude models, so you can use Claude with the existing data service by changing only the connection settings — the Base URL, API key, and OpenAI model fields. You don't need a new data service.

This page builds on Generate or transform values with the data service Custom Prompt With Dynamic Values. Set up the data service as described there, and apply the Claude-specific settings on this page.

You can use this setup to test and evaluate how Claude works with your prompts. Before relying on it for a production feed, contact support@productsup.com so we can advise on the right setup for your use case.

Prerequisites

To use Claude with the Custom Prompt With Dynamic Values data service, you need:

Configure the data service to use Claude

In the settings of your Custom Prompt With Dynamic Values data service, change the following fields.

In Base URL, enter https://api.anthropic.com. Don't add /v1 to the end of the URL.

Leave API version empty.

Caution

Entering a value in API version switches the data service into Microsoft Copilot (Azure OpenAI) mode, which Claude doesn't support. Keep this field empty when you use Claude.

In API key, enter your Claude (Anthropic) API key.

In OpenAI model, enter an exact Claude model identifier, for example claude-sonnet-4-6 or claude-opus-4-8. This field accepts any text and isn't validated, so an invalid identifier fails only when the data service runs. See Anthropic's model overview for the available identifiers.

In Max Response Tokens, set the maximum number of tokens in Claude's response, or leave the field empty to use the platform default of 2048.

Select Save, then select Run in the top-right corner of your site's view to process the data service.

The context, prompt, request timeout, request concurrency, and caching settings work the same way as they do with OpenAI.

A successful run returns Claude's generated values in your column, the same as a run with OpenAI. The platform creates the ___service_ai_custom_prompt attribute containing the generated values.

Limitations

The following limitations apply when you use Claude through this data service:

LimitationDetail
Reasoning effort is ignoredThe Reasoning effort setting has no effect with Claude.
Temperature is capped at 1Claude accepts temperature values from 0 to 1. Values above 1 are silently reduced to 1.
No prompt cachingThis setup doesn't cache prompts on Anthropic's side, which can affect cost and latency on large, high-volume feeds.
Model identifier isn't validatedThe OpenAI model field accepts any text. An invalid Claude identifier fails only when the data service runs.

Troubleshooting

SymptomLikely causeResolution
Not-found error/v1 was added to Base URL, or API version is setEnter https://api.anthropic.com exactly, and clear the API version field
Authentication errorWrong key, or the data service is in Azure OpenAI modeUse a Claude API key, and make sure API version is empty
Model errorInvalid or unavailable model identifierEnter an exact Claude model identifier that your key can access
Output ignores reasoning effortExpected behaviorClaude ignores the Reasoning effort setting

See also

How is this guide?

On this page