Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GLM 5.2GLM 5.3 PrimeA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GLM 5.2 | GLM 5.3 Prime | |
|---|---|---|
| Input per 1M | $0.563 | $2.8 |
| Output per 1M | $1.8 | $8.8 |
| Cached input | $0.105 | $0.56 |
| Batch in / out | n/a | n/a |
| Blended (3:1) | $0.872 | $4.3 |
| Context | 1M | 1M |
| Routes | 27 | 2 |
| Released | Jun 16, 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 5.2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 DeepInfrafp4 · cached $0.105 | $0.563 | $1.8 | $0.563 / $1.8Same as list | $0.105 | Same as list |
| StreamLake fp8 · cached $0.119 | $0.643 | $2.02 | $0.643 / $2.02+13% vs list | $0.119 | +13% vs list |
 Novita AIfp8 · cached $0.121 | $0.65 | $2.04 | $0.65 / $2.04+14% vs list | $0.121 | +14% vs list |
 DigitalOceanDefault region · cached $0.105 | $0.7 | $2.2 | $0.7 / $2.2+23% vs list | $0.105 | +23% vs list |
 CoreWeavefp4 · cached $0.14 | $0.76 | $2.42 | $0.76 / $2.42+35% vs list | $0.14 | +35% vs list |
| AtlasCloud fp8 · cached $0.174 | $0.938 | $2.95 | $0.938 / $2.95+65% vs list | $0.174 | +65% vs list |
 Qwen (Alibaba)fp8 · cached $0.193 | $0.966 | $3.04 | $0.966 / $3.04+70% vs list | $0.193 | +70% vs list |
| Inceptron fp4 · cached $0.194 | $1.01 | $3.24 | $1.01 / $3.24+80% vs list | $0.194 | +80% vs list |
| Phala fp8 · cached $0.22 | $1.26 | $3 | $1.26 / $3+94% vs list | $0.22 | +94% vs list |
 SiliconFlowfp8 · cached $0.221 | $1.19 | $3.74 | $1.19 / $3.74+110% vs list | $0.221 | +110% vs list |
| Baidu fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
 Basetenfp8 · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.14 | +147% vs list |
 Cloudflare Workers AIDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
 Fireworks AIDefault region · cached $0.14 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.14 | +147% vs list |
 FriendliDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
| GMICloud fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
 Parasailfp4 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
 Together AIDefault region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
 Venicefp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
| Wafer Default region · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
| Z.ai fp8 · cached $0.26 | $1.4 | $4.4 | $1.4 / $4.4+147% vs list | $0.26 | +147% vs list |
| Baseten fast, fp8 · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+270% vs list | $0.21 | +270% vs list |
| Fireworks AI fast · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+270% vs list | $0.21 | +270% vs list |
| Fireworks AI fast-us · cached $0.21 | $2.1 | $6.6 | $2.1 / $6.6+270% vs list | $0.21 | +270% vs list |
| Qwen (Alibaba) fast, fp8 · cached $0.462 | $2.31 | $7.26 | $2.31 / $7.26+307% vs list | $0.462 | +307% vs list |
| Baidu fast, fp4 · cached $0.56 | $2.25 | $7.88 | $2.25 / $7.88+319% vs list | $0.56 | +319% vs list |
| Decart fast, fp4 · cached $0.48 | $2.25 | $8 | $2.25 / $8+323% vs list | $0.48 | +323% 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.