Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GLM 4.6GLM 5.3 PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GLM 4.6 | GLM 5.3 Prime | |
|---|---|---|
| Input per 1M | $0.43 | $2.8 |
| Output per 1M | $1.75 | $8.8 |
| Cached input | $0.08 | $0.56 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.76 | $4.3 |
| Context | 205K | 1M |
| Routes | 4 | 2 |
| Released | Sep 30, 2025 | Sep 23, 2026 |
| Leadersboard score | 5 (#30) | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper
Every route
GLM 4.6
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Venicefp4 · cached $0.08 | $0.43 | $1.75 | $0.43 / $1.75Same as list | $0.08 | Same as list |
 DeepInfrafp4 · cached $0.1 | $0.5 | $2 | $0.5 / $2+15% vs list | $0.1 | +15% vs list |
 Novita AIbf16 · cached $0.11 | $0.55 | $2.2 | $0.55 / $2.2+27% vs list | $0.11 | +27% vs list |
| Z.ai fp4 · cached $0.11 | $0.6 | $2.2 | $0.6 / $2.2+32% vs list | $0.11 | +32% 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 |
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.