# webbersites LLM Inference (Claude Haiku)

> webbersites LLM Inference (Claude Haiku) is a paid API for AI agents from api.webbersites.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Runs a single LLM inference call using Claude Haiku 3.5, accepting a prompt and optional system message and returning a generated text response — no API key required, paid per-call via x402.

## Facts

- Endpoint: POST https://api.webbersites.com/api/llm
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/webbersites-llm-inference-claude-haiku-dd7dd52d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_yDELZTKtNP3g9R_0amnCq

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 webbersites-llm-inference-claude-haiku-dd7dd52d -d '<json body>'
```

Example prompt: Summarize the following support ticket in two sentences and classify its urgency as low, medium, or high: 'Our entire checkout flow is broken since the last deploy — no customers can complete purchases and we're losing revenue fast. Please fix ASAP.'

## When to prefer this

Choose this endpoint when you need a quick, keyless LLM inference call — especially for summarization, classification, extraction, or rewriting tasks — and don't want to manage API keys or subscriptions. Ideal for agents that need on-demand AI text generation at a flat $0.01/call price. Not suited for very long outputs (capped at ~1,000 tokens) or multi-turn conversations.

## Known failure modes

- Prompt exceeds 8,000 characters — request rejected with validation error
- System prompt exceeds 2,000 characters — request rejected
- Response truncated at ~1,000 tokens — stop_reason indicates max_tokens hit
- Payment not processed via x402 — 402 Payment Required returned
- Model unavailable or upstream Anthropic error — 5xx response

## How this service works

LLM INFERENCE for keyless agents — POST {prompt, system?} and get Claude Haiku's answer: summarize, classify, extract, rewrite, translate, draft. No API key, no account, no subscription — the x402 payment IS the auth. One flat price per call. Caps: 8,000-char prompt, 2,000-char system, ~1,000-token response (stop_reason tells you if you hit it). Powered by Claude Haiku 4.5.

## Output

A JSON response containing the LLM-generated text completion from Claude Haiku, along with a stop_reason field indicating whether the response ended naturally or was truncated at the ~1,000-token limit.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "required": [
      "prompt"
     ],
     "properties": {
      "prompt": {
       "type": "string",
       "description": "The task/question, up to 8,000 chars"
      },
      "system": {
       "type": "string",
       "description": "Optional system prompt (persona, format rules), up to 2,000 chars"
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "model": {
       "type": "string"
      },
      "usage": {
       "type": "object"
      },
      "response": {
       "type": "string",
       "description": "the model's answer"
      },
      "stop_reason": {
       "type": "string",
       "description": "end_turn, or max_tokens if the 1,000-token cap was hit"
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "claude-haiku-4-5",
  "usage": {
   "input_tokens": 41,
   "output_tokens": 4
  },
  "response": "billing",
  "stop_reason": "end_turn"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/webbersites-llm-inference-claude-haiku-dd7dd52d/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.webbersites.com](https://www.zero.xyz/host/api.webbersites.com/llms.txt)