LLM pricing, compare AI model API prices
Compare the API prices of about 450 LLMs from OpenAI, Anthropic, Google, Meta, Mistral, DeepSeek, Qwen and others: USD per million input and output tokens, context length, max output, modalities, and the cost of your call when you give token counts. Filter by name, provider, price cap, context or image input; sort by input, output or blended price. Source: OpenRouter's public model list. Use to pick the cheapest model that fits a job.
Inputs
| Name | Type | Description |
|---|---|---|
q | string | Words in the model id or name, e.g. gpt, claude, llama 70b |
provider | string | Only this provider: openai, anthropic, google, meta-llama, mistralai, deepseek, qwen… |
maxInputPrice | number | Only models at or under this USD per million input tokens |
minContext | integer | Only models with at least this context length in tokens |
vision | string | true: only models that take image input |
inputTokens | integer | Input tokens of your call, to estimate its cost |
outputTokens | integer | Output tokens of your call, to estimate its cost |
sort | string | input (default), output, blended (3:1 input:output) or context |
limit | integer | Number of models (1-50, default 20) |
Request
Over HTTP, with a card key from /credits:
curl -H "Authorization: Bearer adt_…" "https://agent-data-tools.revmesh2074.workers.dev/llm/prices?q=llama"
Or one of your 25 free calls, no key:
curl "https://agent-data-tools.revmesh2074.workers.dev/llm/prices?q=llama&trial=1"
Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
Example result
{
"count": 1,
"matched": 41,
"sort": "blended",
"models": [
{
"id": "meta-llama/llama-3.3-70b-instruct",
"name": "Meta: Llama 3.3 70B Instruct",
"provider": "meta-llama",
"contextLength": 131072,
"maxOutputTokens": 16384,
"inputPerMillionUsd": 0.1,
"outputPerMillionUsd": 0.25,
"free": false,
"inputs": [
"text"
],
"outputs": [
"text"
],
"estimatedCostUsd": 0.000325
}
],
"source": "OpenRouter public model list (openrouter.ai/api/v1/models)",
"asOf": "2026-11-06T06:00:00.000Z"
}
From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is llm_prices, and the first 25 successful calls are free:
https://agent-data-tools.revmesh2074.workers.dev/mcp