Skip to content
Agents tracked: 444 Releases (7d): 644 Agent status: 3 with issuesSince last limit reset: Claude 31d · Codex 3d Updated Oct 23, 2026
AgentGid
✦ Ask

Model APIs and gateways · by MoonMath.ai

Zro

A hosted inference service for open-weight coding models (GLM, DeepSeek, MiniMax) behind OpenAI- and Anthropic-compatible endpoints, with a CLI that launches Claude Code, Codex, OpenCode and similar tools against it, and per-key EU or US region pinning.

You can point an existing coding agent at cheaper open models by changing a base URL, without request bodies being stored or used for training.

API (paid)Commercial OK

Open zro.moonmath.ai ↗ agent.md

For your project

Official API
Official API · Paid Plans are monthly spend budgets, not token caps: Pro $60 budget, Max $300 budget; inference metered per model; usage packs expire after 90 days
“Zro serves open-weight coding models through OpenAI-compatible and Anthropic-compatible APIs.” zro.moonmath.ai/llms.txt
Key
Needed
“Authorization: Bearer <user generated Zro API key>” zro.moonmath.ai/llms.txt
Formats
JSON
Data download
Not stated
Price
No free tier stated · from $20/mo
“In short: Pro costs $20 per month, Max costs $60 per month, Team costs $500 per month and is coming soon, and Enterprise pricing is custom.” zro.moonmath.ai/docs/plans
License
Zro Terms of Service; upstream model licenses (MIT, GLM-5.3 License, MiniMax Community License) You may build your own apps and agents on Zro but may not resell raw inference access or share keys; each served model also carries its own upstream license
Commercial use
Commercial use OK
“Building your own application or agent on Zro is allowed; reselling raw Zro access is not.” zro.moonmath.ai/terms
Credit
Not stated
Embedding
Embedding unclear
Using the website
Paid

Read on Zro's own pages on Oct 24, 2026 · license or terms · API docs · pricing. Check the license page before you ship.

For your agent

  • Set OPENAI_BASE_URL=https://zro.moonmath.ai/v1 (or ANTHROPIC_BASE_URL=https://zro.moonmath.ai) with a Zro API key as bearer token and a model such as deepseek-v4.1-flash; or `npm install -g @moonmath-ai/zro`, `zro login`, `zro launch claude --model deepseek-v4.1-flash`.
  • Do not resell raw inference access or share API keys with third parties
  • Check each model's upstream license (e.g. GLM-5.3 License, MiniMax Community License) for commercial terms
  • The security-oriented Dolly models are unaligned; use them only on systems you own or are authorized to test

llms.txt: zro.moonmath.ai/llms.txt

Paste into your agent: Read https://agentgid.com/resources/zro/agent.md before using Zro.

Quick answers

Does Zro have an API?

Yes. Zro has an official API documented at https://zro.moonmath.ai/docs/api.

Does the Zro API need a key?

Yes, you need an API key. Limits: Plans are monthly spend budgets, not token caps: Pro $60 budget, Max $300 budget; inference metered per model; usage packs expire after 90 days

Is Zro free?

There is no free tier stated on its pricing page. Paid plans start at $20 a month.

Can I use Zro in a commercial project?

Yes. Its terms say: "Building your own application or agent on Zro is allowed; reselling raw Zro access is not."

What you can build

  • Run Claude Code or Codex against an open model for routine refactors to cut model cost
  • An EU-only coding assistant for a company that needs inference kept in Europe, using a region-restricted key
  • A batch code-review bot that calls the OpenAI-compatible chat endpoint with an open model

Alternatives in Model APIs and gateways

All 7 →

Cohesor You can cut and cap agent model spend by swapping one base URL and key instead of rewriting code for each provider. API (paid)Commercial OK LLMTest A provider outage or a reply that is not valid JSON no longer breaks your feature, because the proxy retries on another model inside the same request, and you see what each AI feature costs. API (paid)Commercial OK Nous Research (Nous Portal inference API) You can call Hermes models through a standard OpenAI client, or download the same weights from Hugging Face and run them yourself. APIDownloadFree tierCommercial: conditions Tokenwise You find out which prompts and models drive your LLM bill by changing one base URL, while your own provider keys pass through and are not stored. API (paid)Free tierCommercial OK Opper AI Switching or pooling model providers becomes a model-string change, and teams that must keep data in the EU get one sub-processor and one DPA instead of a contract per provider. APIFree tierCommercial OK RunInfra You can point Claude Code, Codex, Aider or an existing OpenAI/Anthropic SDK at open models by changing a base URL and key, without renting or tuning GPUs yourself. API (paid)Free tierCommercial OK

Something wrong or out of date? Tell us.