Unified AI model gateway

One API for GPTGPT, Claude, Kimi, Qwen, DeepSeek, GLM, MiniMax and Mimo models

Aggregate many major AI model providers behind one OpenAI-compatible gateway, with user keys, PAYGO balance and usage accounting in the console.

Create an account first. No subscription required.


Start in minutes

From account to API call in three steps

  1. 1

    Create your CodexToken account

    Register with an allowed email domain, then manage keys, balance and usage from the console.

  2. 2

    Top up PAYGO balance

    Add USD-denominated credit through checkout and spend one balance across enabled model groups.

  3. 3

    Create an API key

    Use the OpenAI-compatible base URL in your app, CLI or agent workflow.

Supports many leading AI model providers

  • GPT
  • Claude
  • Kimi
  • Qwen
  • DeepSeek
  • GLM
  • MiniMax
  • Mimo
OpenAI
Claude
Kimi
Qwen
DeepSeek
GLM
MiniMax
Mimo
Model gateway
Route every task
OpenAI Claude DeepSeek GLM
MODEL GATEWAY

Chat and coding models

Use GPT, Claude, Kimi, Qwen, DeepSeek, GLM and MiniMax models behind one consistent API surface.

  • Chat, code and reasoning
  • Provider-level routing
  • Multi-key distribution
Learn more
WORKSPACES

Model workspaces

Test supported chat, coding and reasoning models from the console before moving traffic into production.

  • Prompt testing
  • Model comparison
  • PAYGO accounting
Learn more
LangChain workflow illustration
FRAMEWORKS

LangChain workflows

Point LangChain and agent frameworks at the same base URL while keeping balance, usage and routing centralized.

  • OpenAI-compatible clients
  • Agent workflows
  • Centralized accounting
Learn more
CodexToken chat interface preview
CodexToken Chat
Test before shipping

Use the chat workspace to compare models before moving the same key into production.

Send real prompts, attach supported files and inspect the experience before you wire the API into your product.

  • Supports GPT, Claude, Kimi, Qwen, DeepSeek, GLM, MiniMax and Mimo models configured for your account.
  • PAYGO by default. Top up once and spend across enabled groups.
  • Keep browser testing separate from production API keys.

Why teams use CodexToken

$

One balance for enabled models

Top-up balance is spent across the model groups and routes your account can access.

S

Privacy-minded gateway

User-facing keys are separated from upstream credentials, and sensitive values stay out of the browser.

P

PAYGO

No forced monthly plan. PAYGO balance is deducted from token and model usage.

K

API key control

Create separate keys for apps, experiments and production traffic.

V

Volume support

High-volume users can contact us for routing, limits and pricing discussions.

R

Resilient routing

Requests are distributed across configured upstream keys, with accounting kept at the user level.

Run real AI workloads with one clean control layer

SMOOTH SETUP

CodexToken made our model access much easier to manage. One endpoint, one balance, and much less time spent switching configs.

Ethan BrooksAI product builder
FAST TESTING

The console is clean enough to test prompts quickly, then move the same setup into our agent workflow without extra glue code.

Maya ChenPrompt workflow lead
CLEAR USAGE

It is much easier to understand what our keys are spending. The PAYGO balance and usage view make day-to-day control simple.

Noah CarterAutomation engineer

FAQ

Is there a free plan?

CodexToken is PAYGO-first. You can create an account and open the console; model calls require available balance or granted credit.

Do I need a monthly subscription?

No. PAYGO is the default flow, and an optional monthly plan is available when you want a separate subscription card.

How should I use API keys?

Create separate keys for different projects. Rotate or disable a key if it appears in logs, clients or public repositories.

How is usage billed?

Usage is deducted from your user balance based on configured model pricing and token usage.

Can high-volume users get support?

Yes. Contact us with your expected model mix, traffic pattern and reliability needs.

What if I need a model that is not listed?

Send feedback through the console. New routes can be added when upstream availability and business rules allow it.

Ready

Start with one endpoint for your AI traffic.

Use one console for user keys, balance, model access and usage tracking.

Create Account