Zyverna
Now with agent mode and an OpenAI-compatible API

The AI workspace that ships code with you.

Zyverna pairs frontier models with a real autonomous agent that reads your files, edits them, runs code and iterates until the job is done. Pay for what you use with credits — in USD, CAD, EUR or GBP.

Open the workspace See pricing
3
model tiers
4
currencies
100%
OpenAI-compatible
zyverna · agent
Working
Add rate limiting to the /api/upload endpoint and write a test.

Why Zyverna

Everything an engineer wants from an AI — and nothing they don't.

Designed around how real work happens: reading context, making changes, verifying them, repeating.

A real agent, not a chatbot

Zyverna plans, calls tools, edits files, runs code and checks its own work in a loop — the same way an engineer would.

Workspace-aware

Bring a folder, paste files or start from a template. The agent searches and reads your project before touching anything.

OpenAI-compatible API

Point any existing SDK at api.zyverna.com/v1. Same request shape, same streaming — billed in credits.

Three model tiers

Flash for speed, Core for everyday engineering, Ultra for deep reasoning. Switch per message.

Transparent credits

Every request shows its cost. Top up any amount in USD, CAD, EUR or GBP, and earn bonus credits on larger amounts.

Built for global teams

Multi-currency billing, VAT/GST-ready invoices and localized receipts from day one.

Privacy mode

Zero data retention on Business and Scale. Your code is never used to train models.

Usage you can audit

Per-run token counts, per-key limits and exportable usage logs — no surprises on the invoice.

How it works

From request to verified change in one loop.

Zyverna's agent runs a plan → act → verify cycle with a transparent tool log. You see what it read, what it changed and why — in real time.

  1. 01

    Describe the outcome

    Ask in plain language. Attach files, link a repo or paste an error.

  2. 02

    The agent plans and acts

    It searches, reads, edits and runs — showing every tool call as it happens.

  3. 03

    It verifies its own work

    Tests, type-checks and sanity runs are part of the loop, not an afterthought.

  4. 04

    You review the diff

    Accept, tweak or ask for another pass. You stay in control of what ships.

example.ts
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ZYVERNA_API_KEY,
  baseURL: "https://zyverna.com/api/v1",
});

const stream = await client.chat.completions.create({
  model: "zyverna-core",
  stream: true,
  messages: [
    { role: "user", content: "Refactor this function to be async-safe." },
  ],
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Developer API

Drop-in compatible with the OpenAI SDK.

Change one line — the baseURL — and your existing code talks to Zyverna. Streaming, tool calling and JSON mode all work as expected. Every API key has its own spend limit and usage log.

  • • POST /v1/chat/completions with streaming & tools
  • • GET /v1/models with live credit pricing
  • • Per-key budgets, rotation and revocation
  • • Credits deducted per token with a cost header on every response
Read the API docs

Pricing

Simple plans. Honest credits.

Four plans from $50 a month — or skip the subscription and top up any amount in your currency.

Starter

For solo developers getting serious about shipping with AI.

$40/ mo

Billed $480 yearly

5,500 credits / month

Start with Starter
  • 5,500 credits / month (10% more than pay-as-you-go)
  • All models: Flash, Core, Ultra
  • Unlimited agent runs
  • 3 workspaces
  • API access (OpenAI-compatible)
  • Email support
Most popular

Pro

For professionals who run the agent all day, every day.

$104/ mo

Billed $1,248 yearly

15,000 credits / month

Start with Pro
  • 15,000 credits / month (15% more)
  • Everything in Starter
  • Unlimited workspaces
  • Priority model routing — faster responses
  • Usage analytics & spend alerts
  • Priority support (1 business day)

Business

For small teams that need shared context and controls.

$168/ mo

Billed $2,016 yearly

26,000 credits / month

Start with Business
  • 26,000 credits / month (24% more)
  • Up to 5 seats included
  • Everything in Pro
  • Shared workspaces & team rules
  • SSO (Google, Microsoft, Okta)
  • Privacy mode — zero data retention
  • Admin controls & 90-day audit log

Scale

For organizations with security, compliance and volume needs.

$400/ mo

Billed $4,800 yearly

65,000 credits / month

Start with Scale
  • 65,000 credits / month (30% more)
  • Up to 20 seats included
  • Everything in Business
  • Dedicated model capacity
  • SCIM provisioning
  • Signed DPA & SOC 2 report
  • Dedicated success engineer & SLA
Pay as you go

No subscription? Top up any amount.

Enter whatever you want to spend — from $5 to $5,000 — in USD, CAD, EUR or GBP. Credits never expire, and larger top-ups earn +5%, +10% or +15% bonus credits. Works on its own or on top of any plan.

$USD
You get— credits
Buy credits

Every new account gets 200 welcome credits — no card required. Prices exclude applicable VAT/GST/sales tax, calculated at checkout based on your billing address.

Compare plans and model pricing

Frequently asked questions

A credit is Zyverna's unit of usage. 100 credits = 1 USD. Each model lists its price per 1,000 input and output tokens in credits, and every response shows exactly how many credits it consumed.

Start building with Zyverna today.

200 welcome credits when you sign up — no credit card required. Then pick a plan or top up any amount.

Open the workspace Buy credits