GLM
Coding, agentic workflows, and long-horizon tasks.
R9SAccess leading open modelsthrough one API
Use GLM, DeepSeek, Qwen, Kimi, and MiniMax through an OpenAI-compatible gateway, with transparent per-model pricing, request-level usage records, and one API key.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://gw.r9s.ai/v1",
api_key=os.environ["R9S_API_KEY"],
)
resp = client.chat.completions.create(
model="glm-5.3",
messages=[{"role": "user", "content": "Refactor this module."}],
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://gw.r9s.ai/v1",
apiKey: process.env.R9S_API_KEY,
});
const resp = await client.chat.completions.create({
model: "glm-5.3",
messages: [{ role: "user", content: "Refactor this module." }],
});curl https://gw.r9s.ai/v1/chat/completions \
-H "Authorization: Bearer $R9S_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [
{ "role": "user", "content": "Refactor this module." }
]
}'Leading open model families. One key.
Access supported models from GLM, DeepSeek, Qwen, Kimi, MiniMax, and BAAI through one gateway. Choose the right model for coding, reasoning, long-context, embedding, and reranking workloads.
Kimi
Long-context coding, retrieval, and research workflows.
DeepSeek
Reasoning and coding for cost-sensitive workloads.
Qwen
General reasoning, multilingual, vision, and embedding workloads.
MiniMax
Efficient text and agent workloads across multiple context ranges.
Access and payment, simplified for global developers
One endpoint, supported card payments, transparent pricing, and request-level records in one console.
One endpoint for supported models
Keep the OpenAI SDK and change the base URL, API key, and model ID.
Card payments via PayPal
Pay by supported credit or debit card from $5. Payments are securely processed by PayPal, and no PayPal account is required.
Transparent pricing
See input, output, and cached-input prices before sending traffic.
Request-level usage records
Track request IDs, model usage, API keys, timestamps, and spend in one console.
Send your first request
in minutes
Create an account
Sign up with email, Google, or GitHub. No Chinese phone number required.
Top up from $5
Pay with a supported credit or debit card. Payments are processed by PayPal; no PayPal account is required.
Connect your application
Create an API key, copy the R9S base URL, choose a supported model ID, and run a working example.
Model API usage at cost. Zero service fee.
Choose flexible pay-as-you-go access or custom support for production workloads.
Pay as you go
Pay as you go
Prepaid API usage with no recurring subscription. Access supported open models through one API key and pay only for recorded model usage.
$5minimum top-up
0 service fee- Model API usage at cost
- One API key across supported models
- Usage tracking by model and key
- No recurring subscription
Coding Plan
Coding Plan
Monthly GLM-5.3 access for sustained AI coding workloads, with included usage and plan-specific limits.
From $9.90/ month
Go$9.90
Pro$19.90
Max$99
- Up to $520 included GLM-5.3 usage per billing cycle
- 1, 3, or 8 concurrent requests based on your plan
- GLM-5.3 access within plan limits
- Real-time usage tracking
- No overage charges
EnterpriseEnterprise
For teams running production workloads at volume, with procurement, compliance, and finance in the room.
Custom
- Volume pricing and committed-use rates that improve with scale
- SLA options with a named support channel
- Metering and chargeback by team, project, and cost center
- Invoicing, PO, and annual billing options
- SSO, audit trails, and data-handling review
- Dedicated capacity and onboarding support
Looking for per-model token prices? See the full model list.
The questions everyone asks first
Which models can I use?+
R9S currently provides supported models from GLM, DeepSeek, Qwen, Kimi, MiniMax, and BAAI. See the Models page for current model IDs and pricing.
Do I need a PayPal account to top up?+
No. You can pay directly with a supported credit or debit card. Payments are securely processed by PayPal, but no PayPal account is required.
Do I need a Chinese phone number to sign up?+
No. You can sign up with email, Google, or GitHub. No Chinese phone number is required.
Is there a service fee?+
During the launch period, R9S waives its standard 5% top-up fee. Current token prices are listed on the Models page.
What does OpenAI-compatible mean?+
R9S supports an OpenAI-compatible Chat Completions workflow. Keep your OpenAI SDK and change the base URL, API key, and model ID. Check the documentation for supported endpoints and parameters.
Does R9S retain my prompts?+
R9S processes prompt content to route requests to the selected provider. Our retention practices and the applicable provider policies are described in the Privacy Policy.
Can I request a refund?+
Contact support@r9s.ai to ask whether unused credits are eligible for a refund under the applicable Terms of Service.