Skip to content
APMIX.AI
EN
Free10M free tokens on 2 models at sign-up

One API key for every top AI model.

Point Claude Code, Codex CLI or your own code at api.apmix.ai. GPT, Claude, Gemini, Grok, DeepSeek and Qwen run on a single key and one monthly plan.

See pricingHow it works
  • OpenAI- and Anthropic-compatible endpoints
  • Works with Claude Code, Codex CLI and Cursor
  • Cancel any time
~/app — zsh
claude
ANTHROPIC_BASE_URL=https://api.apmix.ai
ANTHROPIC_API_KEY=apx_live_••••d41e
claude
Claude Code · sonnet-4 · apmix
Rate-limit /login and add tests
Read src/routes/login.ts
Edit src/routes/login.ts
+38 −4
Write tests/login.test.ts
+61
Done · 2 files · 48k tokens
codex
OPENAI_BASE_URL=https://api.apmix.ai/v1
OPENAI_API_KEY=apx_live_••••d41e
codex "soft-delete invoices"
Codex · gpt-5 · apmix
Edit db/schema.ts
+12 −2
Write db/migrations/0042.sql
+19
Run pnpm test 42 passed
Done · 2 files · 31k tokens

API key

Pro plan
apx_live_9f3c••••••••d41e
Base URL
https://api.apmix.ai
Models
11 families

Model families available on apmix

All models

Why apmix

One key. Every model. Your tools.

Stop managing six provider accounts and six invoices. One key and one endpoint cover everything, and your existing tools keep working.

  • One key, every model

    The same API key works for GPT, Claude, Gemini, Grok, DeepSeek and Qwen. Change the model name, nothing else.

  • Drop-in for your CLI

    Set the base URL in Claude Code or Codex CLI. Cursor, SDKs and curl work the same way.

  • One usage meter

    A single monthly allowance shared across every model and every key. Check it in the dashboard or from the API.

  • One monthly bill

    A fixed price you know in advance. No per-token surprises and no separate invoices from each provider.

How it works

Up and running in a minute.

  1. 1

    Choose a plan

    Pick the monthly allowance that fits how much you use.

  2. 2

    Create an API key

    Generate as many keys as your plan allows, from the dashboard.

  3. 3

    Point your tools at apmix

    Set the base URL and the key. Every model in your plan is available from the first request.

Usage

A number you can actually read.

Every plan includes a monthly allowance of weighted tokens. Tokens on fast models count once; tokens on frontier models count more. There are no daily or weekly caps unless you set them yourself.

  • Fast models count 1× per token
  • Frontier models count 3× per token
  • Reasoning modes count 5× per token
  • No daily or weekly caps. Set your own limits if you want them.

This month

124.3M/ 200M weighted tokens

Resets in 12 days

062%200M

Spent by model

  • Claude29.1M
  • GPT22.4M
  • Gemini13.4M
  • DeepSeek9.7M

FAQ

Questions, answered.

Does it work with Claude Code and Codex CLI?

Yes. Set the Anthropic or OpenAI base URL to api.apmix.ai and use your apmix key. Cursor, official SDKs and curl work the same way.

Do I need separate accounts with each provider?

No. One apmix.ai key covers every model in your plan.

Can I use the same key for every model?

Yes. Change the model name in the request; the key and the endpoint stay the same.

What are weighted tokens?

One unit across every model. A token on a fast model counts once, on a frontier model three times, in a reasoning mode five times. One allowance covers all of them.

What happens when I run out of tokens?

Requests return a clear error until the monthly reset, or you move to a bigger plan or buy a one-time usage top-up. Both apply right away.

How much does it cost, and is it cheaper than paying each provider?

Plans start at $4.99 a month for 60M weighted tokens; bigger plans add more models, up to the whole catalog — GPT, Claude, Gemini, Grok, DeepSeek and Qwen — on one key. That is one cheap subscription instead of six pay-as-you-go bills.

How do I cancel?

From your account page, in one click. Your keys keep working until the end of the paid month.

Start with any plan. Change it whenever you like.

Choose your allowance, create a key, and point your tools at apmix.

Get started