Essential Chinese coding models
More allowance for daily coding workflows
High-volume coding and automation
The live APIMaster catalog controls which coding models are available in each plan. The multiplier shown on every model is applied to the complete official input, output, cache-read, and cache-write price.
| Plan | Coding Starter $1 Official-price allowance: $1.00 | Coding Pro $39 Official-price allowance: $39.00 | Coding Max $69 Official-price allowance: $69.00 |
|---|---|---|---|
| How Coding Plan usage is billed | |||
| Validity | 30 days | 30 days | 30 days |
| How Coding Plan usage is billed | Coding Plan provides a shared official-price allowance for 30 days from payment. You can switch between the enabled models with one API key. Each request is charged using the provider's official input, output, cache-read, and cache-write prices multiplied by that model's configured rate. | Coding Plan provides a shared official-price allowance for 30 days from payment. You can switch between the enabled models with one API key. Each request is charged using the provider's official input, output, cache-read, and cache-write prices multiplied by that model's configured rate. | Coding Plan provides a shared official-price allowance for 30 days from payment. You can switch between the enabled models with one API key. Each request is charged using the provider's official input, output, cache-read, and cache-write prices multiplied by that model's configured rate. |
| Models | |||
| deepseek-v4-pro | ×0.500 | ×1.000 | ×0.500 |
| glm-5.2 | ×1.000 | ×1.000 | ×1.000 |
| glm-5.3 | ×0.300 | Not included | Not included |
| gpt-5.6-sol | ×0.030 | Not included | Not included |
| kimi-k2.7-code | ×1.000 | ×1.000 | ×1.000 |
| minimax-m3 | ×1.000 | ×1.000 | ×1.000 |
| qwen3.8-max | ×1.000 | ×1.000 | ×0.350 |
| kimi-k3 | Not included | Not included | ×0.850 |
Coding Plan provides a shared official-price allowance for 30 days from payment. You can switch between the enabled models with one API key. Each request is charged using the provider's official input, output, cache-read, and cache-write prices multiplied by that model's configured rate.
It is the amount of provider list-price usage included in the plan. Your actual payment is the plan price, while requests consume the allowance according to official token prices and the multiplier configured for the selected model.
Input, output, cache read, and cache write are calculated separately using the provider's corresponding official prices. Cache tokens are not counted again as ordinary input tokens.
Yes. You can switch among the models listed in your active plan through the same API access. Each model uses its own displayed multiplier.
Each successful payment starts a new 30-day period. A Coding Plan is not an automatic recurring subscription.
Requests fall back to the existing wallet or ordinary subscription billing when Coding Plan cannot cover the selected model or the remaining allowance is insufficient.
Sign in to compare the live plans, see your current allowance, and purchase or upgrade a Coding Plan.
Catalog last updated: 2026年8月28日