Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GLM 5GLM 5.3 PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GLM 5 | GLM 5.3 Prime | |
|---|---|---|
| Input per 1M | $0.6 | $2.8 |
| Output per 1M | $1.92 | $8.8 |
| Cached input | $0.12 | $0.56 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.93 | $4.3 |
| Context | 205K | 1M |
| Routes | 8 | 2 |
| Released | Feb 11, 2026 | Sep 23, 2026 |
| Leadersboard score | n/a | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
GLM 5
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| GMICloud fp8 · cached $0.12 | $0.6 | $1.92 | $0.6 / $1.92Same as list | $0.12 | Same as list |
| StreamLake fp8 · cached $0.12 | $0.6 | $1.92 | $0.6 / $1.92Same as list | $0.12 | Same as list |
| Baidu fp8 · cached $0.14 | $0.7 | $2.24 | $0.7 / $2.24+17% vs list | $0.14 | +17% vs list |
 SiliconFlowfp8 · cached $0.2 | $0.95 | $2.55 | $0.95 / $2.55+45% vs list | $0.2 | +45% vs list |
 AWS BedrockDefault region | $1 | $3.2 | $1 / $3.2+67% vs list | n/a | +67% vs list |
 Novita AIfp8 · cached $0.2 | $1 | $3.2 | $1 / $3.2+67% vs list | $0.2 | +67% vs list |
 Venicefp8 · cached $0.2 | $1 | $3.2 | $1 / $3.2+67% vs list | $0.2 | +67% vs list |
| Z.ai fp8 · cached $0.2 | $1 | $3.2 | $1 / $3.2+67% vs list | $0.2 | +67% vs list |
GLM 5.3 Prime
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Z.ai API The lab's own API · cached $0.56 | $2.8 | $8.8 | $2.8 / $8.8List price | $0.56 | List price |
 Qwen (Alibaba)Default region · cached $0.56 | $2.8 | $8.8 | $2.8 / $8.8Same as list | $0.56 | Same as list |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.