Enterprise-Grade AI.
Built for India.
Deployed in Amaravati.

Business applications, chatbots, student projects and coding tasks — one OpenAI-compatible API, served from NVIDIA accelerators in Amaravati, Andhra Pradesh, India.

RegisterRead the docs
tokenkey.py
from openai import OpenAI

client = OpenAI(
    base_url="https://tokenkey.in/v1",
    api_key="tk_live_...",
)

client.chat.completions.create(
    model="tk-auto",
    messages=[{"role": "user", "content": "hello"}],
)

One API across the work an institution actually does.

Concrete jobs rather than feature adjectives — if one of these is your problem, the migration is a base URL.

Business applications
Document question-answering, summarisation, drafting and internal tools. Wire it into systems you already run through an API your team most likely already knows.
Chatbots and assistants
Support desks, campus helplines, internal knowledge assistants. Responses stream token by token over your own network rather than a transatlantic round trip.
Student work
Tutoring, explanation and research help at classroom scale. Prompts stay in India and are never stored, so coursework does not become somebody else's training data.
Coding tasks
Completion, review and edits across files, routed to a model tuned for code rather than a general one asked to cope with it.

Different work wants different models.

Ask for tk-auto and the gateway chooses. Name a model and it honours that, verbatim.

tk-auto

Router

Picks the tier for each request before generating, and records which one served it and why.

tk-base

Fast

Short, high-volume requests where responsiveness matters more than depth.

tk-32b

Flagship

Multi-step reasoning and longer context — the questions worth the extra compute.

tk-codercoming shortly

Code

Generation, review and repository-scale edits.

  1. 01

    Classify before generating

    The tier is chosen before a single token is produced. The rejected alternative — letting a small model attempt everything and escalate when it judges itself to have failed — pays both models' latency on the hardest requests, and small models are poorly calibrated about their own competence.

  2. 02

    Serve from the right tier

    A fast tier for short work, a flagship tier for reasoning, a coding tier for repository-scale edits. Naming a model explicitly always overrides the router.

  3. 03

    Account for every token

    Counts, time-to-first-token and the routing decision are recorded per request — including when a client disconnects mid-stream, so abandoned work is not silently free.

Abstract network of connected nodes — the accelerator cluster serving the API

NVIDIA accelerators in Amaravati, Andhra Pradesh.

Andhra Pradesh is building Amaravati as the country's AI capital. Your models run there — on hardware you can point at, under the same laws as the people using it.

Hardware in Amaravati, Andhra Pradesh
NVIDIA L40S accelerators in a rack in Amaravati — not a region name in a cloud console, but a machine with an address you can visit.
Your data stays in India
Inference runs on that hardware and account email goes through an Indian relay. Your text is not forwarded to a model provider abroad, because there is no provider in the path — the model is on the rack.
Content is not stored
Usage records hold token counts, latency and the routing decision — never the text. Retention is off by default, and a test asserts it by sending a marker string through and scanning every table for it.
Drop-in compatible, no lock-in
Point any OpenAI client at a new base URL. No SDK to adopt and no rewrite — which also means the same code moves back off us just as easily.
Why it matters

Your data stays in India. Nothing you send is stored.

Data stays in India

Inference and account email both run on Indian infrastructure. There is no overseas model provider in the path to forward your text to — the model is on our rack in Amaravati.

No content stored

Prompts and completions are never written to disk. Usage records hold token counts, latency and the routing decision — and a canary test asserts every table stays that way.

DPDP readiness

coming shortly

We take data privacy and security seriously, and the architecture reflects it: content is never written to disk, retention is off by default, and the audit trail is append-only and enforced by the database rather than by convention. Work towards full alignment with India's Digital Personal Data Protection Act is underway.

Start sending requests.

Create an account, get a key, point your client at it. New accounts are reviewed before access is granted.

Create an accountTalk to us