Coding PlanToken Aggregation Platform
One API Key to access GLM-5.2, Kimi-K2, MiniMax-M2, Claude, DeepSeek and other mainstream LLMs. Compatible with Cursor / Claude Code / Cline / OpenCode. Plans from ¥9.9/month, free routing offers 100 free calls per day.
...
Service uptime
...
Average latency
...
Channels
...
Supported models
Why choose DX TOKEN
Free routing
Unified entry at dxnt.com/free with 100+ free calls every day. Members get permanently boosted quota via invite rewards.
Smart routing
Custom model-combination routing with primary/backup, round-robin and random strategies. Automatic, imperceptible failover.
Multi-model fusion
Multiple models answer in parallel and a judge model merges the best result. Create shareable presets in one click.
Web search
Append the :online suffix to a model name to auto-search the web. Real-time info is injected into the answer. Supports Bing and DuckDuckGo.
Prompt library
Manage prompts as templates with {variable} dynamic rendering, version control and one-click copy.
AIGC creation
Integrated image and video generation via a unified interface from Volcengine, Alibaba, Baidu and more. Billed per image or per second.
Team features
Create organizations, invite members, and share balance and keys. Ideal for team collaboration and enterprise use.
Bring your own key
Connect your own API providers. Call via {identity}/{model}. Free, no balance deducted, with automatic failover.
Coding Plan
AI coding subscription for developers. Prepay to unlock multi-model discounts, billed per call. Flexible and cost-effective.
Enterprise-grade security
Multi-layer protection for every AI call
TLS 1.3 encryption
All traffic is encrypted with TLS 1.3 to secure communications.
Secure key storage
API keys are stored as bcrypt hashes — irreversible encryption.
Privacy protection
Request logs do not record sensitive content, meeting data-protection requirements.
Real-time monitoring
24/7 system monitoring with automatic alerts on anomalies.
Automatic failover
Traffic automatically switches to backup channels on failure, imperceptible to users.
Rate protection
Multi-dimensional rate limiting (TPM/RPM/IP) prevents abuse and malicious calls.
Get started in 3 steps
Create an account
Register in 30 seconds and get free quota instantly.
Get your API key
Create one in the console with quota and model limits.
Start calling
Just swap the base URL. Fully OpenAI SDK compatible.
Developer friendly
Swap the base URL to integrate. Fully compatible with the OpenAI SDK.
1curl https://www.dxnt.com/v1/chat/completions \2 -H "Authorization: Bearer atk-your-key-here" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "gpt-4o",6 "messages": [7 {"role": "user", "content": "Hello!"}8 ]9 }'
1import openai23client = openai.OpenAI(4 api_key="atk-your-key-here",5 base_url="https://www.dxnt.com/v1"6)78response = client.chat.completions.create(9 model="gpt-4o",10 messages=[{"role": "user", "content": "Hello!"}]11)1213print(response.choices[0].message.content)