# modelprices.xyz Cheapest Function-Calling LLM Leaderboard

> modelprices.xyz Cheapest Function-Calling LLM Leaderboard is a paid API for AI agents from modelprices.xyz, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Returns the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers, with input/output/cache pricing and context window details.

## Facts

- Endpoint: GET https://modelprices.xyz/llm/cheapest/function-calling
- 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/modelprices-xyz-cheapest-function-calling-llm-leaderboard-70d959bc
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fQ54rEccQgJOCATLCJF4h

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-cheapest-function-calling-llm-leaderboard-70d959bc
```

Example prompt: Show me the 50 cheapest AI models that support function calling right now, with their input, output, and cache prices per million tokens — I want to pick the most affordable option for my agent loop.

## When to prefer this

Choose this endpoint when you need to quickly identify the cheapest AI models that specifically support function calling / tool use, and want a pre-ranked leaderboard across 70+ providers rather than querying each provider individually. Ideal for agent orchestration systems that need to minimize inference cost while maintaining tool-call reliability. Prefer this over the general cheapest-LLM endpoint when tool/function-calling support is a hard requirement.

## Known failure modes

- HTTP 402 if payment header is missing or invalid USDC amount
- Stale data if hourly refresh is delayed (up to 1 hour lag)
- Empty or partial results if upstream provider pricing data is unavailable
- Rate limiting if called too frequently without valid payment

## How this service works

Cheapest tool-use LLM leaderboard: the 50 lowest-cost AI models that support function calling / tool use, ranked by token price across 70+ providers. Input, output and cache USD per 1M tokens with context window and modality flags joined in. The cheapest way to pick a model for an agent loop that needs reliable structured tool calls. Refreshed hourly.

## Output

A ranked list of up to 50 AI models supporting function calling / tool use, ordered by cost. Each entry includes model name, provider, input price (USD per 1M tokens), output price (USD per 1M tokens), cache price (USD per 1M tokens), context window size, and modality flags. 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-cheapest-function-calling-llm-leaderboard-70d959bc/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)