# LLM Model Search

> LLM Model Search is a paid API for AI agents from x402.botsmith.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-09-14).

Search the live LLM model catalog by name, provider, or ID substring — or list newest releases — returning context window, modalities, and current USD pricing per million tokens.

## Facts

- Endpoint: GET https://x402.botsmith.dev/models/search
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/llm-model-search-96aa1390
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_rLn8SOfvI3dOHJoXzwRjo

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 llm-model-search-96aa1390
```

Example prompt: Search the LLM model catalog for all Anthropic models and show me their context window sizes and current input/output pricing — return up to 20 results.

## When to prefer this

Use this endpoint when you need to discover, compare, or filter multiple LLM models — especially when your training data may be stale and you need live pricing or recently released models. Prefer the sibling LLM Model Lookup endpoint when you already know the exact model ID and need single-model detail. Use this search endpoint for exploratory queries like 'all models from provider X' or 'models with at least N context tokens'.

## Known failure modes

- Query substring matches nothing — returns empty models array with count 0
- minContext filter too high — no models meet threshold, returns empty results
- limit parameter out of range (below 1 or above 50) — validation error
- Network or upstream catalog failure — service unavailable error
- Payment not processed — 402 response with payment details required

## How this service works

LLM Model Search ($0.004/call): Search the current LLM catalog by substring (matches id, name or provider) or, with no query, list the newest releases. Returns context window, input/output modalities and live USD-per-Mtok pricing - the up-to-date model facts an agent working from a stale training cutoff cannot know. Keyless.

## Output

A JSON object containing a count of matched models, total matched count, and an array of model records each with: canonical ID, name, provider, ISO 8601 first-seen date, context token count, max output tokens, input/output modalities arrays, and live USD pricing per million input and output tokens.

## 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"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "limit"
     ],
     "properties": {
      "limit": {
       "type": "integer",
       "default": 10,
       "maximum": 50,
       "minimum": 1,
       "description": "Max results (default 10)"
      },
      "query": {
       "type": "string",
       "maxLength": 100,
       "description": "Substring to match against id/name/provider, e.g. \"kimi\" or \"anthropic\"; omit for newest"
      },
      "minContext": {
       "type": "integer",
       "maximum": 9007199254740991,
       "minimum": 0,
       "description": "Only models with at least this many context tokens"
      }
     },
     "additionalProperties": false
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "count",
      "totalMatched",
      "models"
     ],
     "properties": {
      "count": {
       "type": "integer",
       "maximum": 9007199254740991,
       "minimum": -9007199254740991,
       "description": "Models returned (after limit)"
      },
      "models": {
       "type": "array",
       "items": {
        "type": "object",
        "required": [
         "id",
         "name",
         "provider",
         "releasedAt",
         "contextTokens",
         "maxOutputTokens",
         "inputModalities",
         "outputModalities",
         "priceInputPerMTok",
         "priceOutputPerMTok"
        ],
        "properties": {
         "id": {
          "type": "string",
          "description": "Canonical id, e.g. \"moonshotai/kimi-k3\""
         },
         "name": {
          "anyOf": [
           {
            "type": "string"
           },
           {
            "type": "null"
           }
          ]
         },
         "provider": {
          "anyOf": [
           {
            "type": "string"
           },
           {
            "type": "null"
           }
          ]
         },
         "releasedAt": {
          "anyOf": [
           {
      
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/llm-model-search-96aa1390/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402.botsmith.dev](https://www.zero.xyz/host/x402.botsmith.dev/llms.txt)