80trust / 100
Llm Cheapest
by modelprices.xyz in AI models & inference
x402 APIPassing, checked 35 min ago
Cheapest-model query: returns the lowest-cost AI models matching your constraints — min_context (tokens), vision/function_calling/reasoning (true), max_input_per_mtok (USD cap), limit (default 5). Add expected_input/expected_output token counts to rank by blended USD per request instead of input price; exclude_preview=true skips pre-release models. Answers 'what is the cheapest model that can do X?' across 2,000+ models and 70+ providers.
GET https://modelprices.xyz/llm/cheapest
Last 30 days
All checks passedSome failedAll failedNot checked
- Uptime
- 100%
- Response time
- 20 ms typical, 39 ms slowest 5%
- Last check
- 35 min ago
- Next check
- any minute now
How to call it
# See the payment challenge (nothing is charged)
curl -i -X GET "https://modelprices.xyz/llm/cheapest?expected_input=2000&expected_output=500&limit=3&min_context=200000&vision=true"import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
const client = new x402Client().register(
"eip155:8453",
new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fmodelprices.xyz%2Fllm%2Fcheapest
const res = await pay("https://modelprices.xyz/llm/cheapest?expected_input=2000&expected_output=500&limit=3&min_context=200000&vision=true");
console.log(await res.json());Example input
{
"expected_input": 2000,
"expected_output": 500,
"limit": 3,
"min_context": 200000,
"vision": true
}Example output
{
"generated_at": "2026-07-14T02:00:00.000Z",
"match_count": 41,
"models": [
{
"cache_read_per_mtok": 0.3,
"confidence": "high",
"first_observed_at": "2026-07-12T18:00:00.000Z",
"id": "claude-sonnet-5",
"input_per_mtok": 3,
"output_per_mtok": 15,
"provider": "anthropic",
"source_url": "https://docs.claude.com/en/docs/about-claude/pricing",
"usd_per_request": 0.0135
}
],
"ranked_by": "usd_per_request"
}Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 35 min ago | Passed | 402 | 8 ms | $0.01 |
| 4 h ago | Passed | 402 | 31 ms | $0.01 |
| 8 h ago | Passed | 402 | 20 ms | $0.01 |
| 11 h ago | Passed | 402 | 9 ms | $0.01 |
| 15 h ago | Passed | 402 | 25 ms | $0.01 |
| 19 h ago | Passed | 402 | 25 ms | $0.01 |
| 23 h ago | Passed | 402 | 110 ms | $0.01 |
| 26 h ago | Passed | 402 | 39 ms | $0.01 |
| 29 h ago | Passed | 402 | 6 ms | $0.01 |
| 35 h ago | Passed | 402 | 13 ms | $0.01 |