# AgentIntel LLM Provider Recommender

> AgentIntel LLM Provider Recommender is a paid API for AI agents from intel.memoryapi.org, paid per call via x402, $0.005/call, status unknown (last checked 2026-09-14).

Returns ranked LLM provider recommendations tailored to a specific agent task, capability requirements, and pricing constraints

## Facts

- Endpoint: GET https://intel.memoryapi.org/x402/intel/recommend
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/intel-memoryapi-org-478fb681
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_146ylqMCiuevO0JL3w44Q

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 intel-memoryapi-org-478fb681
```

Example prompt: Which LLM should I use for my tool-calling agent — I need at least 32k context, support for tool calling, and want to keep costs under $0.50 per million tokens; give me a ranked recommendation with scores and reasoning.

## When to prefer this

Use this endpoint when an AI agent needs to dynamically select or switch LLMs based on task requirements, budget, or capability needs — especially for tool-calling agents, cost-sensitive deployments, or when building routing logic across multiple model providers. Prefer this over static model lists when you need scored, ranked recommendations with reasoning.

## Known failure modes

- No models match the specified constraints (e.g. max_price too low or min_context too high) — returns empty recommendations list
- Invalid parameter types (e.g. non-numeric max_price) — likely 400 Bad Request
- Payment not completed via x402 — endpoint returns 402 Payment Required
- Service unavailable or provider data stale — may return 503 or partial data

## How this service works

x402-powered LLM provider intelligence API. Get recommendations, capability data, and status for AI agent routing decisions. Pay per query in USDC on Base mainnet.

## Output

An ordered list of LLM recommendations, each with model name, provider company, input/output pricing per million tokens, context window, first-token latency, supported capabilities (tool calling, JSON mode, x402 native), a numeric recommendation score, and a human-readable explanation of why each model was chosen.

## Example request

```json
{
 "best_for": "tool_calling",
 "max_price": 0.5,
 "min_context": 32000,
 "tool_calling": "true"
}
```

## Request schema (JSON Schema)

```json
{
 "properties": {
  "input": {
   "required": [
    "method"
   ],
   "properties": {
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "example": {
  "task": "tool_calling",
  "success": true,
  "priority": "quality",
  "recommendations": [
   {
    "why": "top agent score (91/100), excellent tool calling (92/100)",
    "name": "Claude 3.5 Sonnet",
    "rank": 1,
    "slug": "anthropic-claude35-sonnet",
    "recommendation_score": 89
   }
  ]
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/intel-memoryapi-org-478fb681/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from intel.memoryapi.org](https://www.zero.xyz/host/intel.memoryapi.org/llms.txt)