# TensorFeed AI Model Routing

> TensorFeed AI Model Routing is a paid API for AI agents from tensorfeed.ai, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Returns a ranked list of top-N AI models for a given task, combining live pricing, benchmarks, provider status, and latency into a single composite score.

## Facts

- Endpoint: GET https://tensorfeed.ai/api/premium/routing
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/tensorfeed-ai-f2993593
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_23e6UwXw7KhL3Lyb7LZ3r

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 tensorfeed-ai-f2993593
```

Example prompt: Which are the top 5 AI models I should use right now for long-form document summarization, factoring in current pricing, latency, and benchmark scores?

## When to prefer this

Use this endpoint when an agent needs to dynamically route or select the best AI model for a task without manually querying pricing APIs, benchmark leaderboards, and provider status pages separately. Ideal for agents that need a single authoritative ranked answer in one call, especially when cost, latency, and live availability all matter simultaneously.

## Known failure modes

- Invalid or unrecognized task description returns empty or low-confidence rankings
- Provider status data temporarily stale causing outdated availability signals
- N value out of supported range returns error
- Pricing data feed lag causing slightly out-of-date cost figures
- Payment failure (402) if USDC balance insufficient

## How this service works

Top-N AI model recommendation for a task. Joins live pricing, benchmarks, provider status, and latency into a single composite score so an agent gets a ranked answer in one call instead of stitching three free endpoints together.

## Output

A ranked list of top-N AI models for the specified task, each entry containing a composite score derived from live pricing, benchmark performance, provider availability, and latency metrics — giving the agent a single, ready-to-use recommendation without needing to aggregate multiple data sources.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {
      "task": {
       "enum": [
        "code",
        "reasoning",
        "creative",
        "general"
       ],
       "type": "string",
       "description": "Task family the model needs to be good at."
      },
      "top_n": {
       "type": "integer",
       "maximum": 10,
       "minimum": 1,
       "description": "How many models to return ranked, default 3."
      },
      "budget": {
       "type": "number",
       "description": "Max blended USD per 1M tokens."
      },
      "min_quality": {
       "type": "number",
       "maximum": 1,
       "minimum": 0,
       "description": "Minimum acceptable quality score (0 to 1)."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/tensorfeed-ai-f2993593/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from tensorfeed.ai](https://www.zero.xyz/host/tensorfeed.ai/llms.txt)