# Delx Token Estimate

> Delx Token Estimate is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-13).

Estimates GPT-style and Claude-style token counts for a given text payload, returning deterministic results without requiring an API key.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/token-estimate
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-token-estimate-b21af1a7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-H5KlwRX3UYSbtcxlN-aM

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability delx-token-estimate-b21af1a7 -d '<json body>'
```

Example prompt: How many tokens would this text use in GPT-4 and Claude? 'The quick brown fox jumps over the lazy dog. Large language models have transformed how we interact with computers.'

## When to prefer this

Choose this endpoint when you need a fast, keyless, deterministic token count estimate before sending text to GPT or Claude — particularly useful in cost-estimation pipelines, prompt budget guards, or fine-tuning dataset validators where you don't want to call the actual LLM API just to measure token length.

## Known failure modes

- Empty or missing text payload returns a validation error
- Extremely large payloads may be rejected or rate-limited
- Malformed request body returns a 400 Bad Request
- Payment not included or insufficient results in a 402 Payment Required response

## How this service works

Estimate GPT- and Claude-style token counts for a text payload for $0.001 USDC; deterministic and keyless. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

## Output

Returns GPT-style and Claude-style token count estimates for the submitted text, computed deterministically without contacting any LLM API. Results typically include per-model token counts and may include breakdown metadata.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input",
  "output"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "additionalProperties": true
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type",
    "example"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "json"
    },
    "example": {
     "type": "object",
     "additionalProperties": true
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {}
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-token-estimate-b21af1a7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)