Total Requests
0
Real gateway calls
Success Rate
—
Of all requests
Avg Latency
—
ms per call
Cache Hits
0
Served from cache
Request Volume
last 12 callsProvider Split
mini AI0
Groq0
Generated API Keys: 0
Tokens Used: 0
Live Request Feed
| Time | Model | Provider | Tokens | Latency | Status | Prompt Preview |
|---|---|---|---|---|---|---|
| No requests yet — use the AI Playground to make real calls | ||||||
Request Logs
All real gateway calls — no fake data
| ID | Time | Provider | Model | Prompt | Response | Tokens | Latency | Status |
|---|---|---|---|---|---|---|---|---|
| No logs yet | ||||||||
Observability
Live metrics from your real gateway calls
Requests
0
Successes
0
Errors
0
Tokens
0
Provider Health
| Provider | Endpoint | Requests | Avg Latency | Success % | Status |
|---|
Gateway Builder
Build an AI API gateway connected to your provider
ℹ The generated gateway config proxies requests through TechyAI to your chosen provider. Copy the usage snippet to use it anywhere that accepts an OpenAI-compatible API.
Configuration
Semantic Caching
Cache similar prompts
Fallback to other provider
Auto-switch on failure
Rate Limiting
Protect from abuse
Request Logging
Log all requests
Generated Output
Gateway JSON Config
// Click "Generate Config" to build
OpenAI SDK Usage
// Configure above to see snippet
Smart Routing
Route requests across providers
Routing Flow
🌐 Incoming
Any API call
→
🧠 Router
Evaluates rules
→
⚡ mini AI
Primary
→
🔮 Groq
Fallback
→
📤 Response
Unified output
Rules
| Name | Condition | Provider | Model | Actions |
|---|---|---|---|---|
| Default | Always | mini AI | openai-large |
Load Balancer
Distribute traffic across providers
Traffic Distribution
mini AI—
Groq Cloud—
Provider Status
mini AI
text.pollinations.ai/openai
Cloud
api.groq.com/openai/v1
Fallback Config
Auto-failover between providers
Fallback Chain
1️⃣Active
Primary: Pollinations AI — Free tier
Tried first on every request
↓ On 5xx / timeout
2️⃣Active
Fallback: Groq Cloud — llama-3.3-70b
Used when primary fails
Auto-fallback on 5xx
Switch provider on server errors
Timeout fallback (10s)
Switch if no response
AI Playground
mini AI
AI API Key Generator
Groq Cloud generates API keys for your gateway integrations
⚡ Groq Cloud is used as the AI engine to intelligently generate, describe, and configure API keys for your integrations. Each key is a real gateway key for the chosen provider.
🔐 Generate New API Key via cloud
🗝️ Generated Keys
0 keysNo keys generated yet.
Use Groq AI to generate your first key.
Use Groq AI to generate your first key.
How It Works
1. You configure the key name, target provider, and permissions above.
2. Groq Cloud's AI (llama-3.3-70b) generates a secure API key token, usage guidelines, rate limit config, and integration snippet — all tailored to your use case.
3. The key acts as a gateway token — use it in the Authorization header when calling TechyAI Gateway, which then proxies to your target provider.
4. All keys are stored locally in your browser and never sent to any external server.
2. Groq Cloud's AI (llama-3.3-70b) generates a secure API key token, usage guidelines, rate limit config, and integration snippet — all tailored to your use case.
3. The key acts as a gateway token — use it in the Authorization header when calling TechyAI Gateway, which then proxies to your target provider.
4. All keys are stored locally in your browser and never sent to any external server.
Prompt Library
Saved templates for your gateway
Semantic Cache
Reduce API costs with intelligent caching
Entries
0
Hit Rate
0%
Hits
0
Saved (est.)
$0
Cached Entries
| Prompt Preview | Model | Provider | Hits | Cached At |
|---|---|---|---|---|
| Cache is empty | ||||
Guardrails
Content safety and filtering rules
Active Rules
Block PII in prompts
Detect and redact personal info
Max prompt length (4096 tokens)
Reject oversized inputs
Content moderation
Filter harmful content
Prompt injection detection
Block injection attempts
API Keys
Provider credentials
⚠ Keys are stored in your browser localStorage only. Never expose them publicly.
⚡
Pollinations AI
No API key required — free public API
🔑
Groq Cloud
gsk_...DY7 (loaded)
Rate Limits
Control request throughput
Global Limits
Live Counters
Requests/min0 / 60
Tokens/min0 / 100k
Counters update with each real request.
Webhooks
Push gateway events to your endpoints
| URL | Events | Status | Last Triggered | Actions |
|---|---|---|---|---|
| No webhooks configured. | ||||
Settings
Platform configuration
Provider Keys
Platform Config
Auto-log all requests
Log every gateway call
Semantic caching
Cache repeated prompts
Show latency in logs