Supports models from
OpenAI
Anthropic
Google
Meta
Mistral AI
xAI
DeepSeek
Kimi
NVIDIA
Qwen
+ 11 more labs
One gateway · every major model · UPI billing
One API key for every AI model.
Pay with UPI.
One API key that works with every major AI model — GPT, Claude, Gemini, DeepSeek and hundreds more. Add money with UPI, starting at just ₹10. Already using OpenAI? Change one line — your existing code keeps working.
$ curl https://api.aitklabs.in/v1/chat/completions -H "Authorization: Bearer yk_live_…"
Intelligent Request Routing
LIVE
Idle — send a request in the playground to watch a live route.
350+
Models, one key
20+
AI labs supported
99.9%
Failover uptime target
Free
Models included
◈
Keys are hashed, not stored
Your API key is SHA-256 hashed on our end — even we can't read it back. Lose it, revoke it, generate a new one.
◇
Prompts aren't logged
We meter tokens, cost, and latency for billing — never the content of what you send or get back.
✕
Payments verify by signature
Top-ups confirm via a signed webhook, not a client-side callback — a closed tab can't lose your credit.
One API for any model
GPT, Claude, Gemini, DeepSeek, Mistral, Grok, Kimi, Qwen and hundreds more — through one key and one endpoint. The OpenAI SDK works unchanged.
Browse all models →moonshot/kimi-k2.6
Moonshotprimary✦Fireworksfailover
Automatic failover
Some models are reachable through more than one host. If the primary provider errors, we retry the same model elsewhere — same weights, same price, same result. Only if that fails do we suggest an alternative.
How routing works →How it works
Three steps from zero to your first completion.
01
Generate an API key
Create a key in seconds. One yk_live_… key works for every model on the platform — no per-model credentials.
02
Add credits with UPI
Top up in rupees by scanning a UPI QR or opening any UPI app. Balance is metered per token — pay only for what you use.
03
Call one endpoint
Point the OpenAI SDK at the gateway. Pick a model or say auto and the routing engine chooses the best one, with failover.
Why Yantra
A single, billed LLM API — one front door to the whole model ecosystem, paid in rupees over UPI.
One key, every model
Stop juggling a dozen provider dashboards and secrets. Generate one key and reach GPT, Claude, Gemini, DeepSeek, Mistral and local models alike.
Intelligent routing + failover
Ask for a capability — auto:cheap, auto:reasoning, auto:fast — and the engine routes to the right model, retrying on a sibling if a provider errors.
OpenAI-compatible
Drop-in /v1/chat/completions, streaming included. Change two lines — base URL and key — and your existing code just works.
Rupee billing over UPI
No cards, no forex. Recharge with UPI and get transparent per-token pricing in INR, metered to the paisa.
Cost-saving auto mode
Let Yantra pick the cheapest model that satisfies the request, so routine calls cost a fraction of always-on flagship pricing.
Local & private models
Route sensitive workloads to self-hosted Llama or Qwen on your own hardware — same key, same API, zero per-token cost.