Pay for what your loops use. There are no plans and no seats. You add money to a prepaid wallet, and every call is reserved against it before it is made.
Each line is the whole credit spent on that one thing.
* On the default model, GLM 5.3 Flash, where a typical call reads about 3,600 tokens and writes about 150, and a loop run makes about 3.5 calls. A larger model costs more per call: see its prices below.
Per one million tokens.
| Model | Input | Output |
|---|---|---|
| DeepSeek V4 Flash 0423 | $0.28 | $0.56 |
| DeepSeek V4 Flash 0731 | $0.28 | $0.56 |
| DeepSeek V4.1 Flash | $0.60 | $2.40 |
| Gemini 2.5 Flash Lite | $0.20 | $0.80 |
| GPT-5 Mini | $0.50 | $4.00 |
| GPT-5 Nano | $0.10 | $0.80 |
| GLM 5.2 | $2.80 | $8.80 |
| GLM 5.3 Flash (default) | $0.30 | $1.00 |
| For | Price |
|---|---|
| 1,000 schedule firings | $0.30 |
| 1,000 searches | $0.60 |
| 1,000 reranks, added to a search that asks for one | $2.60 |
| 1,000 documents indexed | $1.00 |
| 1,000 pages crawled | $0.02 |
| 1,000 API requests served | $0.02 |
| 1,000 verified emails sent | $0.20 |
How money, budgets and caps work in an account: Money, limits and members.