No need to worry about variable token costs. Leverage all the leading models in a one-time plan, forever.
Five model families behind one key. GLM, Kimi and DeepSeek are available today; Qwen and MiniMax are available upon request.
Available upon request. Tell us your workload and we will enable it for your account.
Available upon request. Tell us your workload and we will enable it for your account.
All models run behind one key. Confirm the models enabled for your API key in your dashboard.
What each model costs per 1M tokens, for input and output.
| Model | Input | Output |
|---|---|---|
| GLM 5.2 | $1.40 | $4.40 |
| GLM 5.3 Flash | $0.15 | $0.50 |
| Kimi K2.6 | $0.95 | $4.00 |
| Kimi K2.7 Code | $0.95 | $4.00 |
| DeepSeek V4 Pro | $1.32 | $3.96 |
| DeepSeek V4.1 Flash | $0.30 | $1.20 |
USD per 1M tokens. Qwen and MiniMax are priced when enabled for your account.
Two ways to pay for the same models.
Gold Pass
$4,999
One-time upfront payment. One lifetime plan.
Up to $36,500 in year-one daily credits
Credits expire daily. No rollover. Value depends on daily use. Year 7 onward lasts while EastRouter operates. Taxes and purchase terms apply.
Pay each model’s token rates.
Top up $100 or more and get bonus credit, from 20% at $100 to 35% at $1,000.
$10
Free trial credit
14 days to use it. No card required.
Test real tasks and compare quality, latency and total cost.
Try for freeOne trial per identity, device and IP. Credit and support terms apply.
Configure the base URL, API key and model ID.
Examples for OpenAI SDK, Codex and Claude Code.
base_url=
base_url=
$10 free trial credit. 14 days to use it. No card required.
Try for free