Developer API · v1

One call. Up to 4 AIs.

Send one question and get answers from GPT, Claude, Gemini, Grok, DeepSeek and more – side by side, in a single JSON response. Build fact-checkers, trading copilots, research bots or your own “second opinion” feature.

1. Create a keyIn your dashboard, logged in with Phantom. 2. Get creditsBurn $QUORUN – 10K tokens = 1 credit. 3. Call /v1/askPay only for answers you get.

Base URLhttps://quorun.space

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.

HTTP header

Authorization: Bearer qr_live_...

Credits & pricing

Every successful answer costs credits. If a model fails, you are not charged for it. Credits never expire and are shared with the chat (they are used there after your daily tier limit).

Model	ID	Credits / answer	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`	string · required	Your question, up to 8,000 characters.
`models`	string[] · required	1–4 model IDs, e.g. `["claude", "gpt", "deepseek"]`.
`mode`	string · optional	`"consensus"` – also returns one merged answer, an agreement score and the points where models disagree (+1 credit).
`web`	boolean · optional	`true` – search the web first and give every model the same sources (+1 credit, only charged when sources are found). The response then includes `sources`; answers cite them as [1], [2]. Links in the question are always opened and read.
`attachments`	object[] · optional	Up to 4 files: `{"name": "chart.png", "type": "image/png", "data": "<base64>"}`. Images (PNG, JPEG, WebP, GIF – max 5 MB) go to vision models, PDFs (max 10 MB) and text files are converted to text for every model.
`history`	object · optional	Previous turns per model: `{"claude": [{"role": "user", "content": "…"}, {"role": "assistant", "content": "…"}]}`

Request

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

Response · 200

{
  "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 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}

Errors & limits

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

Status	Type	Meaning
`400`	invalid_request_error	Missing question, too many models or no available model.
`401`	authentication_error	Missing, invalid or revoked API key.
`402`	insufficient_credits	Not enough credits – burn tokens in your dashboard.
`429`	rate_limit_error	More than 60 requests per minute on one key.

Code examples

Terminal

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

Python

import os, requests

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

JavaScript (Node 18+)

const res = await fetch("https://quorun.space/v1/ask", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.QUORUN_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);

Coming soon

Telegram botA ready-made bot built on this API – ask the Quorum from any chat.

MCP serverUse Quorun as a tool inside Claude, Cursor and other agents.

Pay per call (x402)Agents pay per request on Solana – no API key needed.