Overview.
Your COS API at a glance — keys, traffic, and recent calls.
Active Keys
—
Total Calls
—
Calls Today
—
Avg Confidence
—
Tier Breakdown
Risk Distribution
Recent activity.
No API calls yet.
Make your first call to see activity here.
API Keys.
Create, monitor, and revoke your COS API keys. Click any key to see its usage.
Billing.
Your plan, trial status, and monthly call quota.
—
—
—
Choose a plan.
Launch pricing — rates may change at any time.
Starter
₹5,500
₹3,490 / mo
10,000 API calls / month
- COS + COS² (heuristic + Gemini)
- Auto-correct with sources
- Email support
Choose Starter
Pro
₹18,490
₹14,990 / mo
50,000 API calls / month
- COS + COS² + Bamboo
- Cognitive Cycles (Auto) + Forced Grounding
- Prompt Shield
- Email support
Choose Pro
Growth
₹29,490
₹24,990 / mo
100,000 API calls / month
- COS + COS² + COS³ + Bamboo
- Reasoning Depth + Cognition Intercept
- Adversarial Robustness
- Priority support
Choose Growth
Business
₹65,490
₹59,990 / mo
250,000 API calls / month
- Everything in Growth
- Compliance Engine (GDPR, HIPAA, EU AI Act)
- Memory Hygiene (L8) + Strict Mode
- Domain Specialization + SOC 2-grade receipts
- Dedicated Slack support
Choose Business
Need higher volume, on-premise, or custom SLA? Enterprise starts at ₹2,49,999/mo — Talk to us.
Quickstart.
Get COS running in your app in under 5 minutes.
1 — Get your API key.
Go to the API Keys tab and create a new key.
2 — Install the Python SDK.
pip install cos-sdk
3 — Validate AI text.
from cos_sdk import COS
client = COS(api_key="cos_live_your_key_here")
result = client.validate(
text="According to a 2024 study, 90% of companies use AI...",
tier="bamboo", # recommended — fine-tuned, 97.5% precision
)
print(f"Confidence: {result.confidence_score}")
print(f"Risk: {result.risk_level}")
for claim in result.flagged_claims:
print(f" Flag: {claim.claim}")
print(f" Why: {claim.reason}")
4 — Or use curl directly.
curl -X POST https://cos.protofine.ai/api/v2/validate \
-H "Authorization: Bearer cos_live_your_key_here" \
-H "Content-Type: application/json" \
-d '{
"text": "90% of experts agree that AI is transformative.",
"tier": "bamboo"
}'
5 — Stream results for faster UX.
# Tier 1 arrives instantly (~5ms), deeper tiers stream in
for event in client.validate_stream("AI text", tier="tier_3"):
if event.event == "t1_result":
print("Quick check:", event.result.confidence_score)
elif event.event == "validation_complete":
print("Full result:", event.result.confidence_score)
Reference.
All v2 endpoints require Authorization: Bearer cos_live_xxx
POST
/api/v2/validate
Validate AI-generated text. Returns confidence score, risk level, and flagged claims.
Request body
{
"text": "The AI-generated text to validate", // required
"context": "The original user prompt", // optional
"tier": "bamboo" // tier_1, tier_2, tier_3, or bamboo (recommended)
}
Response
{
"confidence_score": 0.72, // 0.0 to 1.0
"risk_level": "medium", // low, medium, high
"flagged_claims": [
{
"claim": "90% of experts agree",
"reason": "Statistic with no source cited",
"severity": "medium",
"correction": "According to a 2023 Gartner survey, 55%..."
}
],
"tier_used": "tier_2",
"summary": "Found 1 potential issue."
}
POST
/api/v2/validate/stream
Same as /validate but streams results via Server-Sent Events. Tier 1 arrives instantly (~5ms), deeper tiers in 2-5 seconds.
SSE events
event: t1_result
data: {"confidence_score": 0.95, "risk_level": "low", ...}
event: validation_complete
data: {"confidence_score": 0.72, "risk_level": "medium", ...}
event: done
data: {}
POST
/api/v2/shield
Prompt Integrity Shield — scans prompts for injection attacks, jailbreaks, manipulation.
Request body
{
"prompt": "The user prompt to scan", // required
"system_prompt": "Your system prompt" // optional, for context
}
POST
/api/v2/compliance/scan
Compliance Engine — scans AI output against regulatory frameworks (GDPR, HIPAA, EU AI Act, SOC 2).
Request body
{
"text": "AI output to scan", // required
"frameworks": ["gdpr", "hipaa"] // optional, default: all
}
POST
/api/v2/cycle
Cognitive Cycle — adaptive tier escalation. Starts at the cheapest tier and automatically escalates when deeper analysis is needed.
CRUD
/api/v2/rules
Custom Business Rules — create, read, update, delete custom validation rules for your organization.
Methods
GET /api/v2/rules — list all rules
POST /api/v2/rules — create a rule
PUT /api/v2/rules/{id} — update a rule
DELETE /api/v2/rules/{id} — delete a rule
Error responses.
401 — Missing or invalid API key
403 — Tier not allowed for this key
429 — Rate limit exceeded (includes retry_after)
500 — Internal server error
Validation tiers.
T1 Heuristic (~1ms, free) — 9 symbolic rules for fake stats, suspicious URLs, hedging
T2 Gemini Flash (~2s) — Single AI model fact-checks the text
T3 Multi-Model (~3s) — Gemini 2.5 Flash + Gemini 2.5 Flash-Lite consensus
Bamboo Bamboo (~3s, recommended) — Fine-tuned, 97.5% precision, 90% recall
Auto Auto — Smart routing: starts cheap (T1), escalates only when needed