nbgateLog in

One key. Every model.

A flexible AI API gateway for developersstudentsresearchersstartups. Point any OpenAI or Anthropic client at https://api.nbgate.com/v1 and spend one quota across every model in the list.

Get StartedDeveloper Docs

Backed by the world's leading models.

  • ClaudeClaude
  • DeepSeekDeepSeek
  • GeminiGemini
  • ZhipuGLM (Zhipu)
  • OpenAIOpenAI
  • HunyuanHunyuan
  • MoonshotAIKimi (Moonshot)
  • XiaomiMiMoMiMo (Xiaomi)
  • MetaMuse (Meta)

Built for developers, students, researchers, and startups.

models live
44
model brands
9
gateway status
Operational
client protocols
2

Every model, one key.

Grouped by brand, in order. The multiplier is the quota weight; latency and throughput are measured through the live gateway.

OpenAI

OpenAI

7 models

  • Greg/gpt-5.65×vision
  • Greg/gpt-5.6-luna5×vision
  • Greg/gpt-5.6-sol15×vision
Claude

Claude

3 models

  • Greg/claude-opus-520×vision
  • Greg/claude-opus-5-532×vision
  • Greg/claude-sonnet-510×vision
Gemini

Gemini

1 model

  • Greg/gemini-4-argon60×vision
DeepSeek

DeepSeek

9 models

  • Greg/deepseek-v4-flash2×1019 ms260.3 tok/s100%
  • Greg/deepseek-v4-flash-07312×1005 ms173.4 tok/s100%
  • Greg/deepseek-v4-flash-vision-exp2.5×1252 ms100%vision

What a key gets you.

  1. 01

    Two protocols, one key.

    OpenAI clients call /v1/chat/completions. Anthropic clients call /v1/messages. The same key and the same quota cover both, so switching tools means switching a base URL.

  2. 02

    Multipliers in the open.

    Every model declares the weight it charges against your quota, and the number sits in the public model list. You can price a workload before you run it, not after.

  3. 03

    A dedicated endpoint for heavy use.

    Enterprise keys get their own subdomain with raw provider multipliers, separated from shared traffic so a busy hour elsewhere does not become your latency.

Pick your package.

Top up from $1.50 in USDT — quota lands in your wallet instantly, tokens never expire.

Starter

$1.50one-time

  • 100M tokens
  • 60 RPM across all your keys
  • OpenAI and Anthropic compatible
  • Tokens never expire
Buy Starter

Pro

$7one-time

  • 500M tokens
  • 100 RPM across all your keys
  • Token saver optimizer
  • Tokens never expire
Buy Pro

Ultimate

$13one-time

  • 1B tokens
  • 200 RPM across all your keys
  • Token saver optimizer
  • Tokens never expire
Buy Ultimate

Enterprise

$110one-time

  • 10B tokens
  • Custom RPM tier
  • Dedicated VIP subdomain
  • Raw provider multipliers
Buy Enterprise

Comparing tiers? See the full breakdown.

Frequently asked questions.

How do I get an API key?

Sign in with Google, open the dashboard, and create a key — it works immediately. Top up in USDT (or QRIS) and buy token quota from the wallet; no waiting, no manual approval.

Which clients work with nbgate?

Anything that speaks the OpenAI or Anthropic API. Point your client at https://api.nbgate.com/v1, paste your nbgate key, and every model in the catalog is available.

How is my usage counted?

Every model declares a public multiplier — the number sits in the model list. Your quota is deducted by multiplier × tokens, so you can price a workload before you run it.

What happens when my quota runs out?

Requests stop until you buy more quota from the dashboard wallet. Keys never auto-charge and never surprise you.

How do I pay?

USDT (TRC20, BEP20, and more), USDC, LTC, BTC — or QRIS for Indonesian banks. Quota lands in your wallet the moment the payment confirms.

Can I see how models actually perform?

Yes. The model page publishes measured latency, throughput, and success rate from live probes — the same numbers we watch, not marketing claims.