ToolVet
78trust / 100

Chat Completions

by SingIt Ask in AI models & inference

x402 APIPassing, checked 4 h ago

SingIt Ask: Ask a language model without an API key: any model listed at GET /v1/models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen and more; default deepseek-v4.1-flash). OpenAI chat-completions request. Pays actual token cost + 30% + a settlement fee (0.001 USDC on Base, 0.002 on Solana), up to a ceiling that follows the model's price; nothing is charged without an answer.

POST https://ask.singitai.app/v1/chat/completions

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
233 ms typical, 279 ms slowest 5%
Last check
4 h ago
Next check
any minute now

How to call it

POST https://ask.singitai.app/v1/chat/completions

Each call costs $0.003 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://ask.singitai.app/v1/chat/completions
content-type: application/json

{
  "max_tokens": 400,
  "messages": [
    {
      "content": "Where is good coffee near the Colosseum?",
      "role": "user"
    }
  ]
}

Parameters

ParameterTypeRequiredDescription
max_tokensintegerNoThe longest answer, in tokens. The payment ceiling grows with it; the charge follows what was used. Default: 800.
messagesarray of objectYesThe conversation, oldest first.
modelstringNoAny model id from GET /v1/models; the ceiling follows its price. Omit for the default model.
streambooleanNoStreaming is not offered. One of: false.

Example response

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

Example response, 33 lines
{
  "billing": {
    "currency": "USDC",
    "markupAtomic": "2",
    "markupBps": 3000,
    "maxChargeAtomic": "3000",
    "mode": "actual_usage",
    "providerCostAtomic": "6",
    "settlementFeeAtomic": "1000",
    "totalAtomic": "1008",
    "version": 1
  },
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Around the Colosseum, try Caffè Propaganda on Via Claudia or Bar Martini for an espresso with a view.",
        "role": "assistant"
      }
    }
  ],
  "created": 1791932400,
  "id": "singit-ask-1791932400000",
  "model": "singit-ask",
  "object": "chat.completion",
  "usage": {
    "buyer_cost_micro": 6,
    "completion_tokens": 31,
    "prompt_tokens": 14,
    "total_tokens": 45
  }
}

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://ask.singitai.app/v1/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":400,"messages":[{"content":"Where is good coffee near the Colosseum?","role":"user"}]}'

# 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://ask.singitai.app/v1/chat/completions' \
  -H 'content-type: application/json' \
  --data-raw '{"max_tokens":400,"messages":[{"content":"Where is good coffee near the Colosseum?","role":"user"}]}' \
  | 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
4 h agoPassed402233 ms$0.003
8 h agoPassed402306 ms$0.003
11 h agoPassed402205 ms$0.003
15 h agoPassed402279 ms$0.003