# Vextorium LLM Pricing API

> Vextorium LLM Pricing API is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-29).

Returns price per million input/output tokens, context window size, and estimated call cost for 300+ language models from providers like OpenAI, Anthropic, Google, Meta, Mistral, and DeepSeek via OpenRouter

## Facts

- Endpoint: POST https://api.vextorium.com/precios-llm-pago?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/vextorium-llm-pricing-api-b63e7261
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_zC7ekJP8OsQ3Uy0I2ahJk

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 vextorium-llm-pricing-api-b63e7261 -d '<json body>'
```

Example prompt: Search for Claude models sorted by price and show me the cost per million input and output tokens plus the estimated cost of a call with 2000 input tokens and 500 output tokens.

## When to prefer this

Use this endpoint when you need programmatic, up-to-date LLM pricing data across 300+ models from multiple providers in a single call. Prefer it over manual price page lookups or provider-specific APIs when you need to compare costs across OpenAI, Anthropic, Google, Meta, Mistral, and DeepSeek simultaneously. Ideal for agents that need to select the most cost-effective model for a task, estimate budgets, or surface pricing information to users.

## Known failure modes

- Invalid sort order enum value (must be 'precio', 'caro', or 'contexto')
- No models matched the search query — returns empty array
- Negative or zero token counts may produce unexpected cost estimates
- Missing required 'input' wrapper object causes schema validation failure
- Payment failure (x402) if USDC balance is insufficient

## How this service works

Price per million input and output tokens of 300+ language models (OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek...) via OpenRouter, with context window and the estimated cost of one call with your token counts; filter by name or provider, sort by price or context.

## Output

Returns a list of matching language models, each with: model ID, display name, supported modalities, context window in tokens, whether it is free, input price per million tokens in USD, output price per million tokens in USD, and the estimated cost in USD for a single call at the specified token counts. Also returns the total number of matching models, the search query used, and a source attribution note.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "orden": {
   "enum": [
    "precio",
    "caro",
    "contexto"
   ],
   "type": "string"
  },
  "buscar": {
   "type": "string"
  },
  "limite": {
   "type": "integer"
  },
  "tokens_salida": {
   "type": "integer"
  },
  "tokens_entrada": {
   "type": "integer"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/vextorium-llm-pricing-api-b63e7261/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.vextorium.com](https://www.zero.xyz/host/api.vextorium.com/llms.txt)