How Nexpher works

Nexpher turns plain descriptions into working AI agents you can chat with, train, share and sell. This page explains every part of the service.

1. 01Create a free account — no credit card needed. The Free plan includes 50k tokens a month and 200 MB of storage.
2. 02Open the builder and describe your agent in a sentence: “a patient math tutor for 10-year-olds.”
3. 03Chat with the result immediately. Save good exchanges as lessons to train an upgrade later.
4. 04Keep it private, publish it to the marketplace at your own price, or connect it to your own app with an API key.

The builder is a conversation. Tell it who the agent is, how it should talk and what it must never do — it writes the underlying configuration for you and shows a summary before creating anything.

Prefer a head start? Templates give you four pre-configured agents (tutor, support, writer, coder). Pick one from the homepage, tweak the prompt, make it yours.

Every agent runs on a language model. Nexpher ships with fast open models out of the box — pick one from the model picker above the composer.

Each model row in our catalog carries its own price per 1k tokens, so heavier models consume your allowance faster. The picker shows which are enabled and their relative cost.

Have an OpenAI-compatible endpoint — OpenRouter, Groq, Together, even Ollama on your own machine? Register it under Dashboard → Models with its base URL and API key.

Your endpoint appears in the model picker for your account only. Messages routed through it never touch our inference budget — we just relay them.

When an agent answers well, save that exchange as a lesson. Lessons accumulate into a dataset you can review under your agent's Train tab.

Start a training job and we run a LoRA fine-tune — a light-touch process that nudges an open model toward your task instead of rebuilding it. Your base model stays untouched and you can switch back anytime.

Fine-tuning is included on Starter and above — Free accounts can build and chat, but training requires a paid plan because GPU time is billed to us.

Jobs progress through preparing → uploading → queued → running → succeeded, and you can follow them live from the Train page.

Publish any agent to the marketplace with your own description and price per message. Other users install it and pay per message from their wallets.

Creators keep 80% of every message; Nexpher's 20% platform fee covers inference, storage and payments. Earnings land in your wallet ledger instantly and can be paid out once thresholds are met.

Installing someone else's agent works the same way — charges leave your wallet only when you actually message it.

Need raw model access like Fireworks? Mint an inference key (nxi_…) under Dashboard → APIs and call POST /v1/chat/completions with any catalog or BYO model — no agent required.

Prefer a trained assistant? Every agent can get its own nxa_… key so your website, app, or backend talks to that agent directly. Point any OpenAI SDK at the agent base URL.

Team agents work the same way: editors and admins can mint agent keys. Usage is billed according to the team's billing mode (owner, each member, or shared team plan).

curl https://api.nexpher.ai/v1/chat/completions \
  -H "Authorization: Bearer nxi_..." \
  -H "Content-Type: application/json" \
  -d '{ "model": "…", "messages": [{ "role": "user", "content": "Hi!" }] }'

Create a team, invite collaborators, and share agents under one workspace. Roles are owner, admin, editor, and viewer.

Pick how usage is billed: charge the team owner, each member individually, or a shared team plan with its own token pool.

Plans bundle a monthly token allowance plus storage. Tokens are consumed by chatting, training and serving published agents — roughly one token per word of text processed.

Run low? Buy a token pack (stacks until your period ends) or upgrade. Nothing auto-bills beyond your plan; agents pause politely if you hit zero rather than surprising you.

Prices and packs on the pricing page load live from our billing service, so what you see always matches what checkout charges — no stale screenshots.

Nexpher AI is operated by Nexpher Limited. Conversations, training files and trained adapters live in managed storage tied to your account. We do not sell personal data and do not use your content to train unrelated third-party models without your instruction.

Deleting a conversation, dataset or agent removes it from production storage. Full details are in our Privacy Policy, Terms of Service, Acceptable Use Policy and Cookie Policy.