Back to Browse
LLM Pricing Lookup via OpenRouter
x402
LLM Pricing Lookup via OpenRouter is a paid API for AI agents from api.vextorium.com, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-11).
Returns pricing (input/output cost per million tokens), context window size, and estimated call cost for 300+ language models from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, and more — with filtering and sorting.
Price / call$0.002
Success—
StatusUnknown
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
A JSON object listing matching models with their name, model ID, supported modalities, input and output price in USD per million tokens, context window size in tokens, estimated per-call cost in USD based on provided token counts, and a free flag. Also includes total count of matching models, the search query used, and a source note indicating prices are from OpenRouter's public model API.
Example use cases
Find cheapest model for a task
“I need to pick the most affordable LLM that supports long context. Show me models sorted by input price, with a context window over 100k tokens, and estimate what a call with 2000 input and 800 output tokens would cost.”
Compare Anthropic model costs
“Pull up all Anthropic models and their prices per million tokens — I want to see which one is cheapest for a workload with 500 input tokens and 1500 output tokens.”
Budget estimate for GPT usage
“What would it cost to call a GPT-4 model with 3000 input tokens and 1000 output tokens? Show me all OpenAI GPT-4 variants sorted by price so I can pick the best value.”
Technical details
Endpoint
POSThttps://api.vextorium.com/v1/llm-prices?utm_source=zero.xyzWhen to prefer
Use this endpoint when you need programmatic, structured LLM pricing data across many providers at once, especially when estimating costs for specific token budgets or comparing dozens of models simultaneously. Prefer this over manually checking provider websites when you need filtering by name/provider, sorting by cost, or automated cost estimation integrated into an agent workflow. Best when OpenRouter-sourced prices are acceptable (note: direct provider prices may differ slightly).
Side effects
- Invalid sort order enum value returns validation error
- Providing non-integer token counts causes schema rejection
- Empty or no matching results when search query is too specific or misspelled
- Rate limiting or payment failure (x402) if USDC balance is insufficient
- API may return stale prices if OpenRouter's source data is delayed
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| inputrequired | object | |
| output | object |
Output
Schema · Response
{
"type": "json",
"example": {
"note": "OpenRouter prices; the direct provider may differ.",
"total": 33,
"models": [
{
"free": false,
"name": "Anthropic: Claude Haiku 4.5 (batch)",
"model": "anthropic/claude-haiku-4.5:batch",
"modalities": [
"text",
"image"
],
"call_cost_usd": 0.00175,
"context_tokens": 200000,
"input_usd_per_million": 0.5,
"output_usd_per_million": 2.5
},
{
"free": false,
"name": "Anthropic: Claude Sonnet 5.5 (batch)",
"model": "anthropic/claude-sonnet-5.5:batch",
"modalities": [
"text",
"image"
],
"call_cost_usd": 0.0035,
"context_tokens": 1000000,
"input_usd_per_million": 1,
"output_usd_per_million": 5
}
],
"search": "claude",
"source": "OpenRouter (public model API prices)",
"input_tokens": 1000,
"output_tokens": 500
}
}Tags
x402
Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"