GLM 5.2
z-ai/glm-5.2
- context
- 1.05M
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Long context
Overview
GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...
Providers
- AlibabaView Alibaba
- AmbientView Ambient
- AtlasCloudView AtlasCloud
- BaiduView Baidu
- BaseTenView BaseTen
- CloudflareView Cloudflare
- CoreWeaveView CoreWeave
- DecartView Decart
- DeepInfraView DeepInfra
- DigitalOceanView DigitalOcean
- FireworksView Fireworks
- FriendliView Friendli
- GMICloudView GMICloud
- InceptronView Inceptron
- InferenceNetView InferenceNet
- MistralView Mistral
- MorphView Morph
- NebiusView Nebius
- NovitaView Novita
- ParasailView Parasail
- PhalaView Phala
- RekaView Reka
- RelaceView Relace
- SiliconFlowView SiliconFlow
- StreamLakeView StreamLake
- TogetherView Together
- VeniceView Venice
- WaferView Wafer
- Z.AIView Z.AI
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibabaalibaba/fast · fp8 | $2.31 | $7.26 |
| Alibabaalibaba/fp8 · fp8 | $1.12 | $3.52 |
| Ambient | $0.60 | $2.00 |
| AtlasCloud | $0.938 | $2.948 |
| Baidubaidu/fast · fp4 | $2.25 | $7.88 |
| Baidubaidu/fp8 · fp8 | $1.40 | $4.40 |
| BaseTenbaseten/fast · fp8 | $2.10 | $6.60 |
| BaseTenbaseten/fp8 · fp8 | $1.40 | $4.40 |
| Cloudflare | $0.19 | $8.00 |
| CoreWeave | $0.76 | $2.42 |
| Decartdecart/fast · fp4 | $2.50 | $9.00 |
| Decartdecart/mxfp4 · mxfp4 | $0.3575 | $2.20 |
| DeepInfra | $0.5625 | $1.80 |
| DigitalOcean | $0.70 | $2.20 |
| Fireworksfireworks | $1.40 | $4.40 |
| Fireworksfireworks/fast | $2.10 | $6.60 |
| Fireworksfireworks/fast-us | $2.10 | $6.60 |
| Friendli | $1.40 | $4.40 |
| GMICloud | $1.40 | $4.40 |
| Inceptron | $0.69 | $3.15 |
| InferenceNetinference-net | $0.20 | $4.40 |
| InferenceNetinference-net/fp4 · fp4 | $0.198 | $3.40 |
| Mistralmistral/eu | $1.54 | $4.84 |
| Mistralmistral/zdr · nvfp4 | $1.40 | $4.40 |
| Morph | $0.079 | $6.00 |
| Nebius | $1.40 | $4.40 |
| Novita | $0.6496 | $2.0416 |
| Parasail | $1.40 | $4.40 |
| Phala | $1.26 | $3.00 |
| Reka | $1.40 | $4.40 |
| Relace | $0.057 | $4.30 |
| SiliconFlow | $0.70 | $2.20 |
| StreamLake | $0.6426 | $2.0196 |
| Together | $1.40 | $4.40 |
| Venice | $1.40 | $4.40 |
| Waferwafer | $0.19 | $8.00 |
| Waferwafer/us | $0.05 | $7.00 |
| Z.AI | $1.40 | $4.40 |
Alibaba
alibaba/fast · fp8
- input / 1M
- $2.31
- output / 1M
- $7.26
Alibaba
alibaba/fp8 · fp8
- input / 1M
- $1.12
- output / 1M
- $3.52
Ambient
- input / 1M
- $0.60
- output / 1M
- $2.00
AtlasCloud
- input / 1M
- $0.938
- output / 1M
- $2.948
Baidu
baidu/fast · fp4
- input / 1M
- $2.25
- output / 1M
- $7.88
Baidu
baidu/fp8 · fp8
- input / 1M
- $1.40
- output / 1M
- $4.40
BaseTen
baseten/fast · fp8
- input / 1M
- $2.10
- output / 1M
- $6.60
BaseTen
baseten/fp8 · fp8
- input / 1M
- $1.40
- output / 1M
- $4.40
Cloudflare
- input / 1M
- $0.19
- output / 1M
- $8.00
CoreWeave
- input / 1M
- $0.76
- output / 1M
- $2.42
Decart
decart/fast · fp4
- input / 1M
- $2.50
- output / 1M
- $9.00
Decart
decart/mxfp4 · mxfp4
- input / 1M
- $0.3575
- output / 1M
- $2.20
DeepInfra
- input / 1M
- $0.5625
- output / 1M
- $1.80
DigitalOcean
- input / 1M
- $0.70
- output / 1M
- $2.20
Fireworks
fireworks
- input / 1M
- $1.40
- output / 1M
- $4.40
Fireworks
fireworks/fast
- input / 1M
- $2.10
- output / 1M
- $6.60
Fireworks
fireworks/fast-us
- input / 1M
- $2.10
- output / 1M
- $6.60
Friendli
- input / 1M
- $1.40
- output / 1M
- $4.40
GMICloud
- input / 1M
- $1.40
- output / 1M
- $4.40
Inceptron
- input / 1M
- $0.69
- output / 1M
- $3.15
InferenceNet
inference-net
- input / 1M
- $0.20
- output / 1M
- $4.40
InferenceNet
inference-net/fp4 · fp4
- input / 1M
- $0.198
- output / 1M
- $3.40
Mistral
mistral/eu
- input / 1M
- $1.54
- output / 1M
- $4.84
Mistral
mistral/zdr · nvfp4
- input / 1M
- $1.40
- output / 1M
- $4.40
Morph
- input / 1M
- $0.079
- output / 1M
- $6.00
Nebius
- input / 1M
- $1.40
- output / 1M
- $4.40
Novita
- input / 1M
- $0.6496
- output / 1M
- $2.0416
Parasail
- input / 1M
- $1.40
- output / 1M
- $4.40
Phala
- input / 1M
- $1.26
- output / 1M
- $3.00
Reka
- input / 1M
- $1.40
- output / 1M
- $4.40
Relace
- input / 1M
- $0.057
- output / 1M
- $4.30
SiliconFlow
- input / 1M
- $0.70
- output / 1M
- $2.20
StreamLake
- input / 1M
- $0.6426
- output / 1M
- $2.0196
Together
- input / 1M
- $1.40
- output / 1M
- $4.40
Venice
- input / 1M
- $1.40
- output / 1M
- $4.40
Wafer
wafer
- input / 1M
- $0.19
- output / 1M
- $8.00
Wafer
wafer/us
- input / 1M
- $0.05
- output / 1M
- $7.00
Z.AI
- input / 1M
- $1.40
- output / 1M
- $4.40
Use this model
through Nautili
Route requests to GLM 5.2 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.