Lighter GLM-4.5 variant for fast coding assistance and cheaper agents
Specification
zhipuai listing
Context
131K
Max output
98K
Released
2025-07-28
Knowledge cutoff
2025-04
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · zhipuai list price
Input
$0.1195
Output
$0.8964
Cache read
$0.0239
Cache write
free
Available from 26 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| zhipuaivendor | $0.1195 | $0.8964 | $0.0239 | free | 131K | 98K | — |
| submodel · zai-org | $0.10 | $0.50 | — | — | 131K | 131K | — |
| zenmux · z-ai | $0.1165 | $0.2911 | $0.0233 | — | 128K | 96K | — |
| pinstripes · pinstripes | $0.125 | $0.45 | — | — | 128K | 128K | — |
| huggingface · zai-org | $0.13 | $0.85 | — | — | 131K | 98K | — |
| kilo · z-ai | $0.13 | $0.85 | $0.025 | — | 131K | 98K | — |
| nano-gpt · thinking | $0.13 | $0.85 | $0.025 | — | 128K | 98K | — |
| nano-gpt · z-ai | $0.13 | $0.85 | $0.025 | — | 128K | 98K | — |
| novita | $0.13 | $0.85 | $0.025 | — | 131K | 98K | — |
| novita-ai · zai-org | $0.13 | $0.85 | $0.025 | — | 131K | 98K | — |
| openrouter · z-ai | $0.13 | $0.85 | $0.025 | — | 131K | 98K | — |
| siliconflow · zai-org | $0.14 | $0.86 | — | — | 131K | 131K | — |
| siliconflow-cn · zai-org | $0.1494 | $0.8967 | — | — | 131K | 131K | — |
| kyma · kyma | $0.1797 | $1.175 | $0.0338 | — | 131K | 8K | — |
| impossibl · zai | $0.20 | $1.10 | $0.03 | — | 131K | 98K | — |
| llmgateway | $0.20 | $1.10 | $0.03 | free | 128K | 98K | — |
| llmgateway-providers · zai | $0.20 | $1.10 | $0.03 | — | 128K | 98K | — |
| merge-gateway · zai | $0.20 | $1.10 | $0.03 | free | 128K | 98K | — |
| orcarouter · z-ai | $0.20 | $1.10 | $0.03 | free | 131K | 98K | — |
| tempr · zai | $0.20 | $1.10 | $0.03 | free | 131K | 98K | — |
| vercel · zai | $0.20 | $1.10 | $0.03 | — | 128K | 96K | — |
| vercel_ai_gateway · vercel-ai-gateway | $0.20 | $1.10 | — | — | 128K | 96K | — |
| zai | $0.20 | $1.10 | $0.03 | free | 131K | 98K | — |
| zai · zai | $0.20 | $1.10 | — | — | 128K | 32K | — |
| fireworks_ai | $0.22 | $0.88 | — | — | 131K | 96K | — |
| qiniu-ai | — | — | — | — | 131K | 4K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | llmgateway | Cache read | $0.025 |
| 2026-10-22 | llmgateway | Cache read | $0.03 |
| 2026-09-02 | nano-gpt · thinking | Cache read | $0.06 |
| 2026-10-25 | nano-gpt · thinking | Cache read | $0.025 |
| 2026-09-02 | nano-gpt · z-ai | Cache read | $0.06 |
| 2026-10-25 | nano-gpt · z-ai | Cache read | $0.025 |
| 2026-09-02 | zenmux · z-ai | Cache read | $0.02 |
| 2026-09-20 | zenmux · z-ai | Cache read | $0.0233 |
| 2026-09-02 | zhipuai | Cache read | $0.03 |
| 2026-10-20 | zhipuai | Cache read | $0.0239 |
| 2026-09-02 | llmgateway | Input | $0.13 |
| 2026-10-22 | llmgateway | Input | $0.20 |
| 2026-09-02 | nano-gpt · thinking | Input | $0.12 |
| 2026-10-25 | nano-gpt · thinking | Input | $0.13 |
| 2026-09-02 | nano-gpt · z-ai | Input | $0.12 |
| 2026-10-25 | nano-gpt · z-ai | Input | $0.13 |
| 2026-09-02 | siliconflow-cn · zai-org | Input | $0.14 |
| 2026-10-22 | siliconflow-cn · zai-org | Input | $0.1494 |
| 2026-09-02 | zenmux · z-ai | Input | $0.11 |
| 2026-09-20 | zenmux · z-ai | Input | $0.1165 |
| 2026-09-02 | zhipuai | Input | $0.20 |
| 2026-10-20 | zhipuai | Input | $0.1195 |
| 2026-09-02 | llmgateway | Output | $0.85 |
| 2026-10-22 | llmgateway | Output | $1.10 |
| 2026-09-02 | nano-gpt · thinking | Output | $0.80 |
| 2026-10-25 | nano-gpt · thinking | Output | $0.85 |
| 2026-09-02 | nano-gpt · z-ai | Output | $0.80 |
| 2026-10-25 | nano-gpt · z-ai | Output | $0.85 |
| 2026-09-02 | siliconflow-cn · zai-org | Output | $0.86 |
| 2026-10-22 | siliconflow-cn · zai-org | Output | $0.8967 |
| 2026-09-02 | zenmux · z-ai | Output | $0.56 |
| 2026-09-20 | zenmux · z-ai | Output | $0.2911 |
| 2026-09-02 | zhipuai | Output | $1.10 |
| 2026-10-20 | zhipuai | Output | $0.8964 |
More from Zhipu
most-hosted first