Model
Model
z-ai
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Waferwafer/us | fp4 | $0.079 | $1.40 |
| InferenceNetinference-net/fp4 | fp4 | $0.08 | $4.381 |
| InferenceNetinference-net/us | fp4 | $0.08 | $4.381 |
| Rekareka | — | $0.14 | $4.20 |
| Makoramakora/fp4 | fp4 | $0.14 | $4.40 |
| Waferwafer/fp4 | fp4 | $0.179 | $1.40 |
| DekaLLMdekallm | — | $0.18 | $2.95 |
| AkashMLakashml/fp8 | fp8 | $0.19 | $4.40 |
| Morphmorph/fp8 | fp8 | $0.207 | $4.40 |
| Io Netio-net/fp8 | fp8 | $0.49 | $3.20 |
| Inceptroninceptron/fp4 | fp4 | $0.55 | $1.40 |
| DeepInfradeepinfra/fp4 | fp4 | $0.5625 | $2.50 |
| Tenstorrenttenstorrent/fp8 | fp8 | $0.60 | $2.50 |
| Novitanovita/fp8 | fp8 | $0.63 | $1.98 |
| Baidubaidu/fp8 | fp8 | $0.6986 | $2.1956 |
| GMICloudgmicloud/fp8 | fp8 | $0.70 | $2.20 |
| SiliconFlowsiliconflow/fp8 | fp8 | $0.70 | $2.20 |
| Sail Researchsail-research/fp8 | fp8 | $0.75 | $1.00 |
| Sail Researchsail-research/us | fp8 | $0.75 | $1.00 |
| Relacerelace | — | $0.75 | $2.40 |
| Phalaphala | — | $0.84 | $2.64 |
| Decartdecart/fp4 | fp4 | $0.84 | $2.71 |
| DigitalOceandigitalocean | — | $0.91 | $2.86 |
| Alibabaalibaba | — | $1.19 | $3.74 |
| CoreWeavecoreweave/fp8 | fp8 | $1.20 | $4.00 |
| Friendlifriendli | — | $1.26 | $3.96 |
| AtlasCloudatlas-cloud/fp8 | fp8 | $1.40 | $4.40 |
| BaseTenbaseten/fp4 | fp4 | $1.40 | $4.40 |
| BaseTenbaseten/fp4/us | fp4 | $1.40 | $4.40 |
| Cloudflarecloudflare | — | $1.40 | $4.40 |
| Crusoecrusoe/fp4 | fp4 | $1.40 | $4.40 |
| Fireworksfireworks | — | $1.40 | $4.40 |
| Mistralmistral/nvfp4 | nvfp4 | $1.40 | $4.40 |
| Mistralmistral/zdr | nvfp4 | $1.40 | $4.40 |
| Modalmodal | — | $1.40 | $4.40 |
| Nebiusnebius/fp4 | fp4 | $1.40 | $4.40 |
| Parasailparasail/fp8 | fp8 | $1.40 | $4.40 |
| PrimeIntellectprimeintellect | — | $1.40 | $4.40 |
| Togethertogether | — | $1.40 | $4.40 |
| Venicevenice | — | $1.40 | $4.40 |
| Z.AIz-ai/fp8 | fp8 | $1.40 | $4.40 |
| Mistralmistral/nvfp4/eu | nvfp4 | $1.54 | $4.84 |
| BaseTenbaseten/fast | fp8 | $2.10 | $6.60 |
| BaseTenbaseten/us/fast | fp8 | $2.10 | $6.60 |
| Fireworksfireworks/fast | — | $2.10 | $6.60 |
| ModelRunmodelrun/fp4 | fp4 | $2.10 | $6.60 |
| Alibabaalibaba/prime | — | $2.80 | $8.80 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
glm-5.3
glm-5.3-high