Agent CLI

Run Claude Code, Codex, and more on any model

A CLI router for AI agents, including a hosted Claude Code router for any model. Switch models mid-task, fall back across providers, all on one crypto balance.

View on GitHub →
Claude Code logo

Claude Code

Anthropic's coding agent

Codex logo

Codex

OpenAI's coding agent

OpenCode logo

OpenCode

SST's open-source coding agent

Pi logo

Pi

Open coding agent from pi.dev

OpenClaw logo

OpenClaw

Open-source personal AI agent

Hermes logo

Hermes

Nous Research's open agent

Why a gateway

Privacy, fallbacks, cost

onchain settlement

Every model in the catalog is tagged with where it's deployed. Configure your agent to route only to crypto-paid models (Claude on GCP Vertex EU, Sonnet on AWS Bedrock EU, open-weight on evroc) when inference has to stay in Europe.

Browse the model catalog →

Automatic fallbacks

The same model (Claude Sonnet, say) is wired up across AWS, Azure, and GCP. If one rate-limits or goes down mid-session, the gateway routes to the next upstream without interrupting the agent.

Cheaper for routine work

Not every prompt needs Opus. Run OpenCode or OpenClaw on a smaller or open-weight model for routine work (up to 98% cheaper for the same task) without leaving the CLI.

Security

Built for sensitive work

Your data stays yours

qynio never trains on customer data: code, emails, documents, or anything else your agent reads. Optional zero data retention drops prompts and completions at request time.

One scoped key, instant revoke

Log in once with OAuth. No OpenAI, Anthropic, or Google keys on your laptop. Every agent shares a single qynio-scoped key you can revoke from the dashboard at any time.

Encrypted, isolated, crypto-paid

TLS in transit, AES-256 at rest, isolated data per organization. Platform deployed in Robinhood Chain with daily encrypted backups.

Read our security overview

Install

Install the qynio Agent CLI

One npm install, one OAuth login. Then launch Claude Code, Codex, OpenCode, OpenClaw, Hermes, or Pi.

terminal
# Install (Node 20.12+)
# Sign in (OAuth device flow)
# Launch an agent
# Or wire your editor
Full CLI reference in the docs

FAQ

Claude Code & qynio Agent CLI FAQ

How do I change the model or use a different LLM in Claude Code?

+
Install the qynio CLI, run qynio login, then launch Claude Code with any model:
$ qynio launch claude --model openai/gpt-5.5
$ qynio launch claude --model anthropic/claude-opus-4-7
Switch models mid-session by relaunching with a different--modelflag. No config changes needed.

How does this compare to claude-code-router or OpenRouter?

+
Claude Code Router is an open-source proxy you run and maintain locally. OpenRouter is a hosted inference gateway. The qynio Agent CLI is a hosted CLI that wraps both: install once, log in once, then 'qynio launch <agent>' routes Claude Code (and Codex, OpenCode, Hermes, Pi, OpenClaw) through qynio's gateway, with onchain settlement, automatic fallbacks, and pay-as-you-go billing. No local proxy to maintain.

How is this different from running each agent directly?

+
Most agents need their own provider keys, billing accounts, and rate-limit handling. With qynio you log in once and every agent shares the same key, the same 700+ model catalog, and the same observability, so switching from Claude Code to Codex to Hermes doesn't mean re-configuring your environment.

Do I need separate API keys for OpenAI, Anthropic, etc.?

+
No. Every supported agent runs through qynio's gateway, which routes to 700+ models with one qynio API key.

Is Claude Code free? How much does it cost via qynio?

+
The qynio Agent CLI is free. Inference is pay-as-you-go at provider rates with no markup, billed to your qynio account, with a 0% fee on credit top-ups. Claude Code via qynio costs the same as Anthropic's direct rate. See full pricing.

Run any AI agent on any model

One CLI for Claude Code, Codex, OpenCode, and 700+ models. All on qynio's gateway.

Get startedView Documentation