# modelprices.xyz Phi Pricing Table

> modelprices.xyz Phi Pricing Table is a paid API for AI agents from modelprices.xyz, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Returns current per-token pricing for all Phi models (Phi-4, Phi-3.5) across every provider that hosts them, sorted cheapest first.

## Facts

- Endpoint: GET https://modelprices.xyz/phi-pricing
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/modelprices-xyz-phi-pricing-table-b562a73a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_Af7RrPKEQDgbYHOgNlPy4

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 modelprices-xyz-phi-pricing-table-b562a73a
```

Example prompt: Pull up the latest Phi pricing table and show me how much Phi-4 and Phi-3.5 cost per million tokens on every provider — input, output, and batch — sorted cheapest first so I can pick the most affordable host.

## When to prefer this

Use this endpoint when you specifically need to compare inference costs for Microsoft Phi models (Phi-4, Phi-3.5) across all hosting providers simultaneously. Prefer this over a single-model price lookup when you want a full cross-provider comparison sorted cheapest-first. Choose this over the general cheapest-model query when you already know you want Phi specifically and need a full breakdown by tier (input/output/cache/batch).

## Known failure modes

- Pricing data temporarily unavailable if hourly refresh is mid-cycle (may return stale or 503)
- Payment of $0.01 USDC required via x402 protocol; missing or invalid payment returns 402
- No data returned if Phi models are delisted by all providers
- Provider-specific pricing may lag by up to one hour if a provider changes rates mid-cycle

## How this service works

Phi pricing table: what every Phi model costs per token right now — Phi-4, Phi-3.5 — from Microsoft and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Phi inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.

## Output

A normalized pricing table listing every Phi model (Phi-4, Phi-3.5) with per-million-token costs for input, output, cache, and batch tiers, from every provider that hosts them (Microsoft, AWS Bedrock, Azure, Vertex AI, OpenRouter, Fireworks), sorted ascending by price. Data is refreshed hourly.

## 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",
     "properties": {}
    }
   },
   "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/modelprices-xyz-phi-pricing-table-b562a73a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from modelprices.xyz](https://www.zero.xyz/host/modelprices.xyz/llms.txt)