/ month$9.90
Go.
For lighter use, exploration, and personal workflows.
$70 included model usage
Choose Go 
$16 per rolling 7 hours- $30 per rolling 7 days
- Dedicated Plan Key
- 1 parallel request
- Real-time usage tracking
- No overage charges
Choose your plan
Predictable plans for the way you use AI.
Start with lighter personal workflows, use AI every day, or support heavier apps and automation.
Every plan includes GLM-5.3 and GLM-5.3-Flash usage, rolling limits, real-time tracking, and no overage charges.
Most Popular
/ month$19.90
Pro.
For everyday apps, agents, and professional work.
$110 included model usage
Choose Pro - $28 per rolling 7 hours
- $50 per rolling 7 days
- Dedicated Plan Key
- 3 parallel requests
- Real-time usage tracking
- No overage charges
/ month$99
Max.
For power users, high-volume workflows, and automation.
$520 included model usage
Choose Max - $130 per rolling 7 hours
- $235 per rolling 7 days
- Dedicated Plan Key
- 8 parallel requests
- Real-time usage tracking
- No overage charges
Card payments are processed by PayPal. No PayPal account is required. Included GLM-5.3 and GLM-5.3-Flash usage is measured at Token Plan rates: 1x off-peak; 2x from 14:00–18:00 (UTC+8). It is not cash or wallet balance. Availability and current terms are confirmed in the Console.
Use the Previous and Next buttons, swipe horizontally, or focus the cards and use Left, Right, Home, and End. When this section is pinned, scroll down to explore the benefits or scroll up to return.
Why token plan
Built for sustained AI usage.
Use GLM-5.3 and GLM-5.3-Flash for recurring AI workloads that are easier to budget and understand.
R9S keeps usage and plan boundaries visible before they become a surprise.
Predictable monthly cost
Choose a fixed monthly plan with a defined amount of included GLM-5.3 and GLM-5.3-Flash usage.
From$9.90per billing cycle
Limits that protect spend
Requests pause automatically when an active rolling limit is reached and resume after reset.
$0overage charges
One plan, multiple workflows
Use included GLM-5.3 and GLM-5.3-Flash usage across apps, agents, automation, research, content, and coding workflows.
Flexibleacross use cases
Usage you can actually see
Track plan usage, active limits, reset times, and request activity in the R9S Console.
Real timeusage visibility
# Use your existing OpenAI-compatible client
from openai import OpenAI
client = OpenAI(
base_url="<R9S_PLAN_BASE_URL>",
api_key="<R9S_PLAN_KEY>",
)
response = client.chat.completions.create(
model="glm-5.3-plan",
messages=[{"role": "user", "content": "Summarize this report."}],
)# Connect an Anthropic-compatible client or tool
export ANTHROPIC_BASE_URL="<R9S_PLAN_BASE_URL>"
export ANTHROPIC_AUTH_TOKEN="<R9S_PLAN_KEY>"
export ANTHROPIC_MODEL="glm-5.3-plan"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="glm-5.3-flash-plan"
# Copy the Anthropic endpoint and Plan Key from the Console.Work With Your Stack
Use both models
wherever your
workflow runs.
Use GLM-5.3 and GLM-5.3-Flash through OpenAI-compatible and Anthropic-compatible paths for apps, agents, automation, and supported developer tools. Create a dedicated Plan Key, update the base URL, and monitor usage from the Console.
Apps & assistants
AI agents & automation
Need Model API Too
Predictable usage first.
API Gateway when
you need more models.
Token Plan is designed for sustained GLM-5.3 and GLM-5.3-Flash workloads.
R9S also keeps pay-as-you-go access available for teams that need supported open models through one OpenAI-compatible endpoint.
FAQ
Know exactly what you are buying.
What is included model usage?
Included GLM-5.3 and GLM-5.3-Flash usage is measured at Token Plan rates: 1x off-peak; 2x from 14:00–18:00 (UTC+8). It is not cash or wallet balance. Both models share your plan’s billing-cycle allowance and rolling limits.
Which workloads can I use with Token Plan?
Use the plan for supported GLM-5.3 and GLM-5.3-Flash apps, agents, automation, research, content, and developer workflows. Check the Console for current model availability and plan terms.
Which API formats are supported?
OpenAI-compatible and Anthropic-compatible paths are supported. Create a dedicated Plan Key and copy the protocol-specific endpoint from the Console. Use glm-5.3-plan or glm-5.3-flash-plan; ordinary pay-as-you-go model IDs do not work with a Plan Key. Follow the Token Plan guide in our documentation.
Token Plan →Can I still use R9S as a normal API Gateway?
Yes. Pay-as-you-go API access remains available separately for supported open models. Use the Models & API Pricing page to compare token prices.
Do I need a PayPal account?
No. Supported credit and debit card payments are processed by PayPal, and no PayPal account is required.
Your next AI workflow
with a cost you can plan around.
Choose Go, Pro, or Max for predictable monthly usage, and keep
pay-as-you-go API access available when your product needs more models.