Dashboard
Welcome to the MoltSearch API Developer Portal
Credit Balance
API Calls Today
Active Keys
Tier
AI Models
—
Quick Start
67 models across 9 providers, one API key
Ask several models the same question and get one adjudicated answer back —
independent responses, a chairman verdict, a ranking, and a measured agreement score.
Billed per token; max_spend_credits caps any single call.
curl -X POST https://api.moltsearch.ai/v2/debate \
-H "Content-Type: application/json" \
-H "x-api-key: ms_live_YOUR_KEY_HERE" \
-d '{
"query": "Is nuclear power essential to decarbonising the grid?",
"models": ["openai/gpt-5-nano", "anthropic/claude-haiku-4-5", "google/gemini-2.5-flash-lite"],
"chairman": "anthropic/claude-haiku-4-5",
"grounded": true,
"max_spend_credits": 1
}'
import requests
r = requests.post(
"https://api.moltsearch.ai/v2/debate",
headers={
"Content-Type": "application/json",
"x-api-key": "ms_live_YOUR_KEY_HERE",
},
json={
"query": "Is nuclear power essential to decarbonising the grid?",
"models": [
"openai/gpt-5-nano",
"anthropic/claude-haiku-4-5",
"google/gemini-2.5-flash-lite",
],
"chairman": "anthropic/claude-haiku-4-5",
"grounded": True,
"max_spend_credits": 1,
},
)
d = r.json()["data"]
print(d["verdict"]["text"])
print("agreement:", d["agreement_score"])
for a in d["answers"]:
print(a["model"], "->", len(a["answer"]), "chars")
const res = await fetch("https://api.moltsearch.ai/v2/debate", {
method: "POST",
headers: {
"Content-Type": "application/json",
"x-api-key": "ms_live_YOUR_KEY_HERE",
},
body: JSON.stringify({
query: "Is nuclear power essential to decarbonising the grid?",
models: [
"openai/gpt-5-nano",
"anthropic/claude-haiku-4-5",
"google/gemini-2.5-flash-lite",
],
chairman: "anthropic/claude-haiku-4-5",
grounded: true,
max_spend_credits: 1,
}),
});
const { data, meta } = await res.json();
console.log(data.verdict.text);
console.log("agreement:", data.agreement_score);
console.log("charged:", meta.billing.credits_charged, "credits");
Want a single model instead of a debate? POST /v1/chat
is still supported and flat-priced at 0.1 credit per call.
Full reference at docs.moltsearch.ai.