One call. Up to 4 AIs.

Authentication

Send your API key as a bearer token. Keys start with qr_live_, belong to your wallet and draw from its credit balance. Keep them secret – never put them in frontend code.

Authorization: Bearer qr_live_...

Credits & pricing

Every successful answer costs credits – 1 per standard answer, 5 per premium answer. If a model fails, you are not charged for it. Credits never expire and are shared with the chat, where they kick in after your daily tier limit.

Model	ID	Credits / answer	Images	Status
GPT-6 Astra	gpt	5		Live
Claude Opus 5	claude	5		Live
Gemini 3.1 Pro	gemini	5		Live
Grok 4.6	grok	5		Live
DeepSeek V4 Pro	deepseek	1	–	Live
Mistral Medium 3.5	mistral	1		Live
Cohere Command A+	cohere	1		Live
Llama 4 Maverick	llama	1		Live
Qwen 3.8	qwen	1	–	Live
Kimi K3	kimi	1		Live
GLM-5.3	glm	1	–	Live
Perplexity Sonar Pro	sonar	1	–	Soon
Amazon Nova Premier	nova	1	–	Soon
MiniMax M3	minimax	1	–	Soon
Nemotron 3 Ultra	nemotron	1	–	Soon
Xiaomi MiMo V2.5 Pro	mimo	1	–	Soon

POST /v1/ask

Ask up to 4 models at once. Models are queried in parallel; the response arrives when all of them have answered.

Request body

{
  "question": "Is ETH more likely to flip BTC in market cap by 2030?",
  "models": ["deepseek", "mistral", "kimi"],
  "mode": "consensus"
}

{
  "id": "q_3f9a1c2b7d4e8f01",
  "created": 1790000000,
  "results": {
    "deepseek": { "ok": true, "text": "Unlikely…" },
    "mistral":  { "ok": true, "text": "Low probability…" },
    "kimi":     { "ok": false, "error": "…" }
  },
  "consensus": {
    "agreement": 78, "verdict": "reached",
    "consensus": "Most likely not by 2030…",
    "agreed": ["…"],
    "disagreements": [{ "topic": "…", "positions": [{ "models": ["Kimi K3"], "view": "…" }] }],
    "judge": "Grok 4.6"
  },
  "usage": { "credits_charged": 3, "credits_remaining": 497 }
}

GET /v1/models

Lists all models with their IDs, price in credits, whether they read images and whether they are live. No authentication needed.

GET /v1/credits

Returns the credit balance of the wallet that owns the API key: {"credits": 498}

Consensus mode

With "mode": "consensus", one model chairs the panel after the answers arrive. It doesn’t average them – it merges what they agree on and names each side of every split, with the models on it.

Models that can’t see an attached image are left out of the verdict, so “I can’t see the chart” never counts as a vote. For agents: branch on consensus.agreement – proceed above 70, escalate to a human below 40.

Errors & limits

Errors return JSON: {"error": {"type": "…", "message": "…"}}

Code examples

curl https://polymynd.xyz/v1/ask \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"question": "Fact-check: the Bitcoin halving happens every 4 years.", "models": ["deepseek", "mistral", "kimi"], "mode": "consensus"}'

import os, requests

r = requests.post(
    "https://polymynd.xyz/v1/ask",
    headers={"Authorization": f"Bearer {os.environ['API_KEY']}"},
    json={"question": "Review these tokenomics for red flags: ...", "models": ["deepseek", "qwen", "glm"], "mode": "consensus"},
    timeout=180,
)
r.raise_for_status()
data = r.json()
print(data["consensus"]["agreement"], data["consensus"]["verdict"])
for model, answer in data["results"].items():
    print(f"--- {model}\n{answer.get('text') or answer.get('error')}")

const res = await fetch("https://polymynd.xyz/v1/ask", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ question: "BTC long 64k, SL 61.5k, TP 72k – what am I missing?", models: ["deepseek", "mistral"] }),
});
const { results, usage } = await res.json();
console.log(results, usage.credits_remaining);

Roadmap