LLM routing and Codex account visibility

Route your models.
Know your capacity.

Connect coding agents and apps to a single LLM gateway. Track your personal Codex accounts, weekly quotas, reset dates, and usage in the same dashboard.

Check accessRead the docs

Continue to ZergAI to check current account access. Existing users can sign in.

  • Bring provider API keys
  • Compare model usage
  • Monitor Codex capacity

Your tool → ZergRouter → your model

Keep the client. Choose the route.

A Router key connects supported clients. Model availability depends on credentials, permissions, and protocol support.

curl https://zergrouter.com/v1/responses \
  -H "Authorization: Bearer $ZERGROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "model": "gpt-5.6", "input": "ship it" }'
Get a key and send your first request →

01 / Routing

One endpoint for your tools

Use provider API credentials with scoped Router keys. Choose models, set limits, and configure explicit fallback chains for supported chat requests.

Routing behavior →

02 / Subscriptions

See your Codex capacity

Compare accounts by remaining weekly quotas, each quota’s reset date, and banked resets. Stale data stays clearly marked. API keys and personal subscriptions are separate access paths.

How account monitoring works →

03 / Usage

Understand what ran

Explore routed usage by model, date, and client. See input, cached input, and output where providers report them. Account-wide Codex history does not invent missing token breakdowns.

Understand usage data →

Available route / open-model inference

DeepSeek 4.1 Flash

Connect through Modal Shared Endpoints using the registered Router alias. Access is subject to your Router’s permissions and available platform capacity.

modal/deepseek-v4.1-flash

Use the same Router endpoint and request log as your other models. Provider limits apply; check your authenticated catalog before connecting a client.

Try the DeepSeek quickstart →

Works where you work

Your tools, with explicit compatibility.

Start in the Zerg ecosystem or connect a client you already use. Each tool uses the protocol it supports; model discovery is scoped to your Router.

ZergAI

Create your Zerg identity and use it to sign in across the stack.

Zerg

Build and run autonomous software agents on the Zerg platform.

ZTC

Work with agents from a fast, terminal-native coding environment.

ZDE

See agent work, files, and execution state in a visual workspace.

Codex

Point the Codex Responses provider at one ZergRouter endpoint.

Pi

Bring your routed model catalog into the Pi coding agent.

OpenCode

Use ZergRouter as an OpenAI-compatible provider in OpenCode.

A few useful distinctions

Does a Router key include a model subscription?

No. A Router API key authenticates your routed requests. Provider API credentials and personal Codex subscription accounts are separate; adding one does not grant access to the other.

Can I use DeepSeek with Codex?

Use a model advertised by /v1/models?capability=codex_responses. The Modal route supports native Responses forwarding; the authenticated catalog is the authority for your available models.

How do I get access?

Continue to ZergAI to check current account access. Existing users can sign in. Access and any billing requirements are confirmed in ZergAI, not inferred from this page.

Check access