Zhipu API Pricing
9 models · From $0.070/1M to $2.80/1M input
The cheapest Zhipu model to run is GLM-4.7-FlashX at $0.070 input and $0.400 output per 1M tokens. On a RAG answer of 8,000 tokens in and 600 out, Zhipu models range from $0.0008 (GLM-4.7-FlashX) to $0.028 (GLM-5.3 Prime) per request. The largest context window is GLM-5.3-Flash at 1.0M tokens. Count tokens with the Zhipu token counter.
| Model | Input /1M | Output /1M | RAG answer |
|---|---|---|---|
| GLM-4.7-FlashX | $0.070 | $0.400 | $0.0008 |
| GLM-5.3-Flash | $0.150 | $0.500 | $0.0015 |
| GLM-4.7 | $0.600 | $2.20 | $0.0061 |
| GLM-5 | $1.00 | $3.20 | $0.0099 |
| GLM-5 Turbo | $1.20 | $4.00 | $0.012 |
| GLM-5.3 | $1.40 | $4.40 | $0.014 |
| GLM-5.2 | $1.40 | $4.40 | $0.014 |
| GLM-5.1 | $1.40 | $4.40 | $0.014 |
| GLM-5.3 Prime | $2.80 | $8.80 | $0.028 |