Skip to content

Trust & verifiability

What you can verify about QuickSilver Pro

The LLM API resale market has a real fraud problem: some providers quietly serve a cheaper or heavily-quantized model while billing for the premium one. It works because most users can't tell — you get an answer, not a receipt for which model produced it. We think the answer is verifiability, not promises. Below are the commitments we hold ourselves to, and concrete checks you can run to hold us to them.

  1. You requestYou requestmodel: "deepseek-v4-pro"
  2. Response echoesResponse echoes · matches what you sent"model": "deepseek-v4-pro"Matches what you sent
  3. Cost reconciles withCost reconciles with public per-token ratesusage.cost ⇄ /pricing.jsonPublic per-token rates
  4. Availability is public atPer-model uptime and latency, public at/statusPer-model uptime and latency
  5. And you can testAnd you can test — run them on anyone6 independent checksRun them on anyone

Our commitments

Seven promises, each tied to evidence you can check.

  • When you call deepseek-v4-pro, you get DeepSeek V4 Pro — never a cheaper model quietly swapped in to widen our margin. The model field on every response echoes back exactly the model ID you sent. We do not reroute requests to a different model behind your back.

    model field · checks 1–2

How to verify what you're getting

Don't take our word for it. None of these checks require anything beyond the OpenAI-compatible API you already use — run them against us, and against any provider you're comparing.

  1. Every chat-completions response includes a model field. Confirm it matches what you requested. It's the cheapest check and a provider doing crude substitution often leaks an inconsistent or generic value here.

    ResponseSample shape
    { "object": "chat.completion",
      "model": "deepseek-v4-pro",
    ✓ matches request
      "usage": { … } }
    
POST /v1/chat/completionsSample shape · values vary per call
You sent"model": "deepseek-v4-pro"
{
  "object": "chat.completion",
  "model": "deepseek-v4-pro", (✓ matches request)
  "choices": [ … ],
  "usage": {
    "prompt_tokens": …,
    "completion_tokens": …,
    "cost": …
  }
}

Check 1 of 6 · Evidence: returned ID equals requested ID.

One check that does NOT work: Asking the model "what model are you?". Models infer their identity from the system prompt and their training data — any model trained on GPT-4 transcripts will happily claim to be GPT-4. Self-identification proves nothing.

Limits

Be honest with yourself about the limits: no end-user text probe proves model identity with certainty, and very heavy quantization can evade even the statistical tests. The only real cryptographic proof is hardware (TEE) attestation — the response signed inside a secure enclave bound to the loaded model. That's provider-side work and it's on our roadmap; we'll publish here when it's live. Until then, running these probes — against us and against anyone you compare us to — makes silent substitution expensive to hide. If a check ever fails on QuickSilver Pro, tell us — we treat it as a P0.

Verify it for yourself

Top up $5, run the checks above, and decide. Your first top-up is matched 100%, up to $50 in bonus credits, added on your next top-up.

Get API Key