Gateway opening soon · keys not available yet
Meruva
Meruva Gateway · for developers

Stop juggling lab accounts. One key.

Qwen, DeepSeek, Kimi, GLM and more through one OpenAI-compatible endpoint, with your coding agent set up in five minutes and a real person to help.

Coming soon5-minute setup
# Run your coding agent on an open model (example)
export ANTHROPIC_BASE_URL="https://api.meruva.ai/anthropic"
export ANTHROPIC_AUTH_TOKEN="MERUVA_API_KEY"
export ANTHROPIC_MODEL="kimi-k2"
claude

# Or any OpenAI SDK
base_url = "https://api.meruva.ai/v1"
model    = "deepseek-chat"   # change one string
# Example endpoints and model names; final values in the docs.
Problems, fixed

What gets in the way, and what we do about it.

A console per lab

Separate accounts, top-ups and dashboards for every model family.

One account, one balance, one dashboard.

Different formats

Every provider's endpoint and parameters differ slightly.

OpenAI-compatible, plus Anthropic-style for coding agents.

Agent setup by trial and error

Agent config, base URLs and model names take an afternoon.

Copy-paste guides and a paid set-up session for teams.

Surprise bills

Hard to see what each call or session cost.

Prepaid credit and usage per key and per model.

Cache pricing is a mystery

Cache reads can cut agent costs, if you know how they're billed.

Cache reads priced separately and explained.

Lock-in

Switching providers means rewriting integrations.

Open-weight models, standard API. Change the base URL and go.
How it works

Three steps to your first call.

Coming soon You cannot sign up, top up or get a key yet.

1

Sign up and top up by card through Stripe, when we open.

2

Create a key in the dashboard.

3

Connect your tools. Paste the key into your app or coding agent, then watch usage and spend.

Coming soon
Models

Open models only.

FamilyGood for (examples)
QwenGeneral coding and chat, long context
DeepSeekReasoning and low-cost bulk work
KimiAgentic coding and tool use
GLMWriting, review and structured work
MoreAdded as labs release them

Model strengths are examples; the live list will be on the models page. Prices on Pricing, marked as examples until final.

Also in the package

Meruva Agent Orchestrator.

Open-source agents that run on these models, with human approval gates at plan, design and merge. Being open-sourced, and not available yet.

Ready?

Your first call in five minutes.

Coming soon
Sensitive data?

Keep it in your jurisdiction.

The same models, deployed on your own infrastructure.

See Sovereign