OpenAI-compatible · live now

One API for every AI model

Access hundreds of large language models through a single, OpenAI-compatible endpoint. No infrastructure, no per-provider contracts — sign up and ship in minutes.

Free account · API key in seconds · Pay only for what you use

quickstart.sh
# Already use the OpenAI SDK? Change one line: the base URL.
curl https://modeldatabase.com/v1/chat/completions \
  -H "Authorization: Bearer $MDB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4-8",
    "messages": [{"role":"user","content":"Hello!"}],
    "stream": true
  }'

Hundreds of models from every major provider

Claude Opus 4.8 Claude Sonnet 4.6 GPT-class models Gemini Llama Mistral DeepSeek Qwen + many more
Why Model Database

Everything you need to ship with LLMs

One account, one key, one bill — across every model you want to use.

Drop-in compatible

Fully OpenAI-compatible /v1/chat/completions. Keep your existing SDK and tooling — just point the base URL at us.

🧠

Every major model

Switch between Claude, GPT-class, Gemini, Llama, Mistral and hundreds more by changing a single model string.

🌊

Streaming built in

Token-by-token server-sent events out of the box, so your chat UIs feel instant without extra plumbing.

💳

Pay as you go

Prepay credits and spend them across any model. No subscriptions, no minimums, no surprise invoices.

🔑

Keys in seconds

Create an account, generate a key, and make your first call before your coffee gets cold. Rotate or revoke anytime.

📊

Usage you can see

Per-request cost, model, and status in your dashboard. Every response returns balance and charge headers.

Get started

From zero to first call in 3 steps

Create your account

Sign up with an email and password. You'll get an mdb_live_ API key instantly.

Add some credit

Top up your balance from the dashboard. Credit works across every model — no per-provider setup.

Point & call

Set base URL to modeldatabase.com/v1, pass your key as a Bearer token, and send requests.

Create your free account →
Pricing

Simple, usage-based credit

Prepay a credit pack, then pay only for the tokens you actually use. Credit never expires.

Starter
$10 credit

Perfect for prototyping and testing.

  • Access to every model
  • OpenAI-compatible API
  • Streaming responses
  • Unlimited API keys
Get started
Scale
$200 credit

For high-volume workloads.

  • Everything in Most popular
  • Best value top-up
  • Bulk usage at the same rates
  • Revoke & rotate keys anytime
Get started

All packs draw down per request at transparent token rates. Need a custom volume agreement? Reach out from your dashboard.

FAQ

Questions, answered

Is it really compatible with the OpenAI SDK?

Yes. The endpoint mirrors /v1/chat/completions, including streaming. In most codebases you only change the base URL to https://modeldatabase.com/v1 and use your Model Database API key.

Which models can I use?

Hundreds — spanning Claude, GPT-class models, Gemini, Llama, Mistral, DeepSeek, Qwen and more. You pick a model by passing its identifier in the model field. Call GET /v1/models with your key to list everything available.

How does billing work?

You prepay a credit pack ($10, $50, or $200) from your dashboard. Each request draws down your balance based on the tokens used. Every response includes headers showing the cost of the call and your remaining balance.

How fast can I get started?

Seconds. Create an account, copy your mdb_live_ key, add credit, and make your first call. No sales calls, no waitlist.

Can I manage and revoke keys?

Yes. Create as many keys as you like, label them, and revoke any of them instantly from your dashboard if one is compromised or no longer needed.

Start building today

Join developers shipping faster with one API for every model.

Get your API key →