ToolVet
43trust / 100

Llm Chat

by clinkagent.com in AI models & inference

x402 APIFailing, checked 1 h ago

Claude API for AI agents, pay per token, no API key or account - POST an Anthropic Messages request (messages, system, tools, tool_choice, thinking) and get the full response back. Claude Opus 5, Sonnet 5, Haiku 4.5. Tool calling / function calling supported. Billed on actual usage at list price + 25%, capped at $0.25 per call (x402 upto scheme). LLM inference, chat completions, keyless Claude, Anthropic proxy. Free price sheet: /llm/models.

POST
https://clinkagent.com/llm/chat
Price
$0.25
per call in USDC
Uptime
86.5%
last 30 days
Response time
312 ms
546 ms slowest 5%
Last check
Failed
1 h ago, next in 25 h

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Latest check failed 1 h ago: Expected HTTP 402, got 410

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://clinkagent.com/llm/chat

Each call costs $0.25 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://clinkagent.com/llm/chat
content-type: application/json

{
  "max_tokens": 64,
  "messages": [
    {
      "content": "Say hi in five words.",
      "role": "user"
    }
  ],
  "model": "haiku"
}

Parameters

ParameterTypeRequiredDescription
max_tokensintegerNo1-4096, default 1024
messagesarrayYesAnthropic Messages API messages array; first role must be user
modelstringNo One of: haiku, sonnet, opus, claude-haiku-4-5, claude-sonnet-5, claude-opus-5.
systemstringNoOptional system prompt
toolsarrayNoOptional tool definitions (Anthropic tool-use schema)

Example response

The provider's example. We can't check it without paying.

{
  "content": [
    {
      "text": "Hi there, nice to meet you!",
      "type": "text"
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 8
  }
}

Call it from code

The curl command shows the payment challenge.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://clinkagent.com/llm/chat' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":64,"messages":[{"content":"Say hi in five words.","role":"user"}],"model":"haiku"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://clinkagent.com/llm/chat' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":64,"messages":[{"content":"Say hi in five words.","role":"user"}],"model":"haiku"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode

We don't show code that pays this service: it uses a payment scheme other than exact, which needs a different client setup.

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
1 h agoExpected HTTP 402, got 410410316 ms-
6 h agoExpected HTTP 402, got 410410447 ms-
10 h agoExpected HTTP 402, got 410410402 ms-
14 h agoExpected HTTP 402, got 410410259 ms-
18 h agoExpected HTTP 402, got 410410443 ms-
Show 10 older checks
21 h agoExpected HTTP 402, got 410410328 ms-
24 h agoExpected HTTP 402, got 410410413 ms-
27 h agoPassed402205 ms$0.25
30 h agoPassed402225 ms$0.25
33 h agoPassed402290 ms$0.25
36 h agoPassed402205 ms$0.25
41 h agoPassed402339 ms$0.25
46 h agoPassed402350 ms$0.25
2 days agoPassed402302 ms$0.25
2 days agoPassed402420 ms$0.25