Sep 2026
Accounts
Sign up with email and password; API keys and usage are now private to your account.
TrivaNexus is the model gateway for AI agents: an OpenAI-compatible API that sends each request to the model best suited to it, fails over when providers break, and shows you exactly where every token went.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://agentic.trivanexus.com/api/v1",
apiKey: process.env.TRIVA_API_KEY,
});
// "adaptive" picks the right model for every request
const res = await client.chat.completions.create({
model: "adaptive",
messages: [{ role: "user", content: "Refactor this function" }],
});22+ models from
Put an AI assistant on your website, code with an agent at your side, and run every model through one key — with the usage in plain sight.
Do you deliver to Arusha?
Yes! Delivery takes 1–2 days 🚚
Can I pay with mobile money?
Of course, mobile money or card 👍
A self-serve AI assistant that learns your pages, answers visitors around the clock and hands tricky chats to your team. Paste one script tag and it's live.
Add it to your sitesrc
auth.ts
signup.ts
db.ts
schema.ts
export async function signup(input) {
const user = await db.create(input);const user = await db.create(input);
+ const data = schema.parse(input);
+ const user = await db.create(data);
return user;
}
Validate the signup input
Editing signup.ts…
✓ 12 tests passed · ready to commit
The code editor with the Triva Agent built in. Ask for a change in plain words, review the diff, run the tests and ship.
Download Triva CodeOpenAI-compatible access to DeepSeek, Qwen, Llama, Gemini, Grok and more. Adaptive routing picks the model; failover keeps your agents answering.
Read the docsTokens this week
1.28M
Key · prod-agent68%
of today's budget
Routed to
Qwen412k
DeepSeek288k
Gemini156k
Per-key budgets, live token and cost metering, and model allow-lists, so a runaway agent never surprises you at the end of the month.
Open the dashboardEverything between your agent and the model — routing, reliability, tools and control — in one endpoint.
Every request is scored for complexity and sent to the right tier — quick fixes to fast models, architecture work to frontier ones. One conversation stays on one model so caching keeps working.
If a provider errors, the next one is tried. When nothing can answer you get a clear 502 or 503 — never a fake reply dressed up as a real one.
Streaming, tool calling and a gateway-side file tool loop in a sandboxed workspace, so coding agents like Cline work out of the box.
Approve which models your team can use, set a default, and tune the adaptive tiers and strategy from the admin console.
Per-key daily budgets, token and cost metering, and a live view of which models adaptive mode actually routed to.
No SDK to learn and nothing to self-host.
Sign up, open the dashboard and create an API key. Keys are yours alone and can be revoked any time.
Create accountChange the base URL of any OpenAI-compatible SDK or agent. No new libraries, no new request format.
Read the docsRequest model "adaptive" and each turn is routed to a model that can serve it — escalating a tier if a call fails.
Browse modelsTrack usage per key, see routed models per tier, and adjust budgets and allow-lists as your team grows.
Open dashboardAnything that speaks the OpenAI chat completions API can use TrivaNexus — just change the base URL.
Cline
VS Code coding agent
Continue
IDE assistant
OpenAI Node SDK
baseURL
OpenAI Python SDK
base_url
LangChain
ChatOpenAI
cURL / HTTP
/v1/chat/completions
OpenRouter
hundreds of upstream models
Local models
llama.cpp · Ollama · vLLM
Sep 2026
Sign up with email and password; API keys and usage are now private to your account.
Sep 2026
One model id that routes each request to the right tier and stays consistent across a conversation.
Sep 2026
Current-generation models, with old ids kept as aliases.
Sep 2026
Failed or unconfigured providers return 502/503 instead of placeholder text.
Guardrails for your accounts, keys and agents are built in, not bolted on.
Account passwords are stored as salted scrypt hashes.
httpOnly, SameSite cookies; only a hash of each session token is stored.
Keys are generated from a secure random source and scoped to their owner.
Daily token limits stop a runaway agent from draining your balance.
Admins decide which models can be used across the organization.
Gateway file tools are jailed to a workspace; path traversal is blocked.
Free to start. Bring your own client, keep your code.