Spend less on API. Build more with AI.

Connect powerful models to your coding tools and AI agents through one API. Get started with your existing setup and pay only for the tokens you use — no monthly subscription.

Get API key Compare costs

Models

GLM-5.3-Flash

reasoning
Context
390K
Max output
8,192
Input $/1M
$0.027
Output $/1M
$0.08
API id: zai-org/GLM-5.3-Flash
OpenAI & Anthropic API compatible

For complex coding & reasoning

Use this model
Popular

DeepSeek-V4-Flash

Context
380K
Max output
32,768
Input $/1M
$0.0221
Output $/1M
$0.10
API id: deepseek-ai/DeepSeek-V4-Flash-0731
OpenAI & Anthropic API compatible

For everyday tasks on a budget

Use this model

MiniMax-M2.7

Context
200K
Max output
8,192
Input $/1M
$0.05
Output $/1M
$0.15
API id: MiniMaxAI/MiniMax-M2.7
OpenAI & Anthropic API compatible

For agents & workflow automation

Use this model

GLM-5.3-Flash · zai-org/GLM-5.3-Flash

At 50M tokens

How this is calculated

Calculated for 50M tokens: 75% input and 25% output. Totals are rounded; savings are calculated before rounding.

OpenRouter
$4.30
CheapTokens
$2.01

You save

$2.29

53.2% less than OpenRouter

Get API key

75% input · 25% output tokens

Your next API call starts here.

Create an account, add balance, and connect your model.

  1. Create your account Sign up by email with a magic link. No password.
  2. Add balance Pay only for the tokens you use.
  3. Connect your model Set the API URL, your key, and the model ID.

No subscription. Pay per token.

Create your account

Sign up with your email

Enter your email and we send you a one-time sign-in link. Open it and your account is ready — there is no password to set or remember.

  • Only an email is needed — no names or identity documents.
  • Your API key appears in the dashboard after your first top-up.
Create account

Already have an account? Log in

Add balance

Top up a USD balance

You pre-fund a balance in USD, and every request is charged at the model's fixed per-token rate. When the balance runs out, requests pause until you top up.

Payment
Crypto, or card through a partner
Minimum
$5 with crypto
Deposit fee
5% — card partners charge their own fees on top
Subscription
None. Unused balance does not expire.
Top up balance See pricing

Connect your model

curl 
curl https://api.cheaptokens.dev/v1/chat/completions \
  -H "Authorization: Bearer $CHEAPTOKENS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3-Flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
from openai import OpenAI

client = OpenAI(
    base_url="https://api.cheaptokens.dev/v1",
    api_key="YOUR_CHEAPTOKENS_KEY",
)
resp = client.chat.completions.create(
    model="zai-org/GLM-5.3-Flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cheaptokens.dev/v1",
  apiKey: process.env.CHEAPTOKENS_API_KEY,
});
const resp = await client.chat.completions.create({
  model: "zai-org/GLM-5.3-Flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.cheaptokens.dev",
    api_key="YOUR_CHEAPTOKENS_KEY",
)
msg = client.messages.create(
    model="zai-org/GLM-5.3-Flash",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}],
)
print(msg.content[0].text)
Read the setup guide

Your tools. Connected.

Connect CheapTokens to your coding tools and AI agents.

Cline Claude Code Cursor OpenClaw Aider

Cline

Cline Example setup
API Provider OpenAI Compatible
Base URL https://api.cheaptokens.dev/v1
OpenAI Compatible API Key YOUR_CHEAPTOKENS_KEY
Model ID zai-org/GLM-5.3-Flash
Open setup guide

Claude Code

terminal 
# Claude Code → cheaptokens (Anthropic-compatible)export ANTHROPIC_BASE_URL="https://api.cheaptokens.dev"export ANTHROPIC_API_KEY="YOUR_CHEAPTOKENS_KEY"export ANTHROPIC_MODEL="zai-org/GLM-5.3-Flash"export ANTHROPIC_DEFAULT_HAIKU_MODEL="zai-org/GLM-5.3-Flash"claude

This relies on Claude Code's documented base-URL setting. Anthropic does not officially support non-Claude models in Claude Code, so features built around Claude may behave differently — try your own workflow first.

Open setup guide

Cursor

Cursor Settings › Models Example setup
zai-org/GLM-5.3-Flash

API Keys

OpenAI API Key YOUR_CHEAPTOKENS_KEY
Override OpenAI Base URL https://api.cheaptokens.dev/v1

Per Cursor's documentation, your own key works with chat models only. Tab completion and Cursor's own models keep running on Cursor.

Open setup guide

OpenClaw

~/.openclaw/openclaw.json 
{  models: {    providers: {      cheaptokens: {        baseUrl: "https://api.cheaptokens.dev/v1",        apiKey: "YOUR_CHEAPTOKENS_KEY",        api: "openai-completions",        models: [{ id: "zai-org/GLM-5.3-Flash", name: "GLM-5.3-Flash" }],      },    },  },  agents: {    defaults: { model: { primary: "cheaptokens/zai-org/GLM-5.3-Flash" } },  },}

Fresh install? openclaw onboard with the Custom provider choice asks for the same three values and writes this entry for you.

Open setup guide

Aider

terminal 
export OPENAI_API_BASE="https://api.cheaptokens.dev/v1"export OPENAI_API_KEY="YOUR_CHEAPTOKENS_KEY"aider --model openai/zai-org/GLM-5.3-Flash
Open setup guide

Before you start.

How do I connect my tool?

Point any OpenAI- or Anthropic-compatible client at our API address, add your API key and set the model ID. OpenAI-style clients use the address ending in /v1; Anthropic-style clients use the root address. The quickstart builds a ready-made snippet for your SDK or tool.

Open the quickstart

How does payment work? Is there a subscription or a minimum top-up?

There is no subscription. You top up a USD balance with crypto or by card through a partner, and each request is charged at the model's fixed per-token rate. The minimum top-up with crypto is $5, and a 5% deposit fee applies; card partners charge their own fees.

See pricing

Why is the price lower?

We serve open-weight models on cost-efficient infrastructure and publish fixed USD rates per million input and output tokens for each model. You pay for tokens only — there are no plans or seat fees on top.

Open cost calculator

What are the model limits?

Each model has its own context window and maximum output size — the exact numbers are on its card, up to 390K tokens of context in the current catalog. If your balance runs out, requests return a 402 error until you top up. A model can be temporarily unavailable; its card shows that status.

See all models