ActionAnthropicUpdated September 2026
How do I count tokens before sending a Claude message?
Short answer: You can count tokens in Anthropic by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Anthropic Count Tokens action to a workflow, map its 2 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.
Inputs
The fields this action accepts.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Required | Model. Options: Claude Opus 4, Claude Sonnet 4, Claude Haiku 3.5 |
Message Content content | string | Required | Message Content. e.g. "The text to count tokens for" |
Sample request
{"model": "{{trigger.model}}","content": "The text to count tokens for"}
Returns
{"input_tokens": 42}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Count Tokens.
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Count Tokens.
What does the Count Tokens action do in Anthropic?
Counts the number of tokens a Messages API call would consume without actually sending the message. Useful for cost estimation and to stay under context-window limits.
What inputs does Count Tokens require?
Required: Model, Message Content. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Anthropic returns an error?
The run history shows the failed step with its input and the error message Anthropic returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.
Does Count Tokens support batch operations?
Run Count Tokens inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Anthropic's rate limits.
More actions
Other Anthropic actions.
Action
Analyze Image
Sends an image to Claude for analysis (vision), via URL or base64 bytes alongside a text prompt. Use for OCR, chart extraction, accessibility alt-text, or visual QA flows.
ActionCancel Message Batch
Cancels a message batch that is still processing. Already-completed entries in the batch keep their results; in-flight ones get cancelled with no charge.
ActionComputer Use
Sends a message with the computer-use tool, letting Claude take screenshots and click/type on a virtual desktop. Requires Opus 4.x or Sonnet 4.x; you provide the sandboxed desktop environment.
ActionCreate Message
Sends a message to a Claude model and gets a response. The core Anthropic action; supports system prompts, multi-turn conversation, temperature, and stop sequences.
ActionCreate Message Batch
Creates a batch of messages for async processing on the Messages API, with a 50% cost reduction and up to 24-hour turnaround. Perfect for bulk classification, summarization, or labeling jobs.
ActionCreate Message with Tools
Sends a message with tool definitions. Claude returns tool_use blocks when it wants to call a function; you execute the call and feed results back as tool_result blocks for the next turn. The foundation for agentic workflows.