GLM-5.2: API pricing, providers and specs
GLM-5.2 is a text model by Zhipu AI. 44 providers serve it, from $1.80 to $7 /1M; the lowest price is at FastRouter.
A newer version is out: GLM-5.3 · released Aug 25, 2026
How GLM-5.2 compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $1.80 /1M against a median of $1.10; 61% of comparable models cost less.
- Its 1M-token context window is larger than 67% of them (median 262K), about 1500 pages of text.
- On LMArena's WebDev board it ranks #23 of the 64 comparable models scored there.
- 44 providers serve it; 99% of comparable models have fewer.
- Its weights are open under the MIT license: commercial use allowed.
GLM-5.2 prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Deep Infra | $0.563/1M | From$1.80/1M | $0.105/1M | — |
 FastRouter | $0.563/1M | $1.80/1M | $0.105/1M | 1.05M |
 Opper | $0.15/1M | $2.20/1M | $0.04/1M | — |
 Boundless | $0.34/1M | $2.30/1M | $0.17/1M | — |
 Requesty | $0.75/1M | From$2.40/1M | $0.14/1M | 262K |
 Hugging Face | $0.75/1M | From$2.40/1M | — | — |
| Vercel AI Gateway | $0.80/1M | From$2.55/1M | $0.16/1M | 1M |
| Atlas Cloud | $0.938/1M | $2.95/1M | $0.174/1M | — |
| APIMart | $0.914/1M | $3.20/1M | — | — |
 Cortecs | $0.904/1M | $3.25/1M | $0.19/1M | — |
 Kenari | $0.276/1M | $3.31/1M | $0.051/1M | — |
 CometAPI | $1.12/1M | $3.53/1M | $0.224/1M | — |
 CrazyRouter | $1.10/1M | $3.85/1M | — | — |
 Alibaba | $1.10/1M | $3.85/1M | — | — |
 SiliconFlow | $0.833/1M | $3.89/1M | — | — |
 AIHubMix | $1.13/1M | From$3.94/1M | $0.282/1M | 1M |
| DevPass (LLM Gateway) | $1.26/1M | From$3.96/1M | $0.234/1M | — |
 APIYI | $1.14/1M | $4/1M | — | — |
 LaoZhang API | $1.14/1M | $4/1M | — | — |
| SiliconFlow | $1.30/1M | $4.09/1M | $0.26/1M | — |
| Z.AIOfficial | $1.40/1M | $4.40/1M | $0.26/1M | — |
| ZenMux | $1.40/1M | $4.40/1M | $0.26/1M | 1M |
 CrossModel | $1.20/1M | $4.40/1M | $0.30/1M | — |
 Alibaba | $1.40/1M | From$4.40/1M | — | — |
 Ofox | $1.40/1M | $4.40/1M | $0.26/1M | 1.05M |
 Novita AI | $1.40/1M | $4.40/1M | $0.26/1M | — |
 Cloudflare Workers AI | $1.40/1M | $4.40/1M | — | — |
 Vertex | $1.40/1M | $4.40/1M | $0.14/1M | — |
 Venice AI | $1.40/1M | $4.40/1M | $0.26/1M | — |
| OpenCode | $1.40/1M | $4.40/1M | $0.26/1M | — |
| Baseten | $1.40/1M | From$4.40/1M | $0.14/1M | — |
 OrcaRouter | $1.40/1M | $4.40/1M | $0.26/1M | 1M |
| AI/ML API | $1.40/1M | $4.40/1M | $0.26/1M | — |
 Impossibl | $1.40/1M | $4.40/1M | $0.26/1M | — |
 EmpirioLabs AI | $1.40/1M | $4.40/1M | $1.40/1M | 1M |
 Together AI | $1.40/1M | $4.40/1M | $0.26/1M | — |
| BytePlus | $1.40/1M | $4.40/1M | $0.26/1M | — |
 Jiekou.AI | $1.40/1M | $4.40/1M | $0.26/1M | — |
 TensorX | $1.50/1M | $4.50/1M | $0.38/1M | — |
 Poe | $1.52/1M | $4.55/1M | $0.303/1M | 256K |
 Charm Hyper | $1.52/1M | $4.79/1M | $0.152/1M | — |
 Prime Inference | $1.54/1M | $4.84/1M | — | — |
 Azure | $1.54/1M | From$4.84/1M | $0.15/1M | — |
| OpenRouter | $0.034/1M | From$7/1M | $0.033/1M | 1.05M |
- FastRouter$1.80
- Deep InfraFrom$1.80
- Opper$2.20
- Boundless$2.30
- RequestyFrom$2.40
- Hugging FaceFrom$2.40
- Vercel AI GatewayFrom$2.55
- Atlas Cloud$2.95
- APIMart$3.20
- Cortecs$3.25
- Kenari$3.31
- CometAPI$3.53
Specs
- Type
- Text
- Maker
- Zhipu AI
- Inputs
- Text
- Outputs
- Text
- Context
- 1M≈ 1500 pages of text
- Max output
- 128K
- Capabilities
- Prompt caching, JSON, Reasoning, Tool calling
- Released
- Jun 16, 2026
- License
- MITcommercial use allowed
- Open weights
- Yes, downloadable
- Parameters
- 753B
- Arena score
- 1604WebDev
- Monthly searches
- 109K
Alternatives to GLM-5.2
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| GLM-5.2this model | $1.80/1M | 1M | 1604 | 44 |
| Qwen3.8 2.4T A95B | $4.11/1M | 1M | — | 22 |
| Grok 4.7 | $4.80/1M | 500K | 1637 | 28 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Muse Spark 1.3 | $4.25/1M | 1.05M | 1657 | 11 |
 Sonar | $1/1M | 127K | — | 9 |
| Grok Build 0.1 | $1.60/1M | 256K | — | 18 |
| Gemini 3.8 Flash | $3/1M | 1.05M | 1585 | 30 |
More from Zhipu AI
GLM-5.3Zhipu AI$1.10/1MGLM-5.3-FlashZhipu AI$0.20/1MGLM-5Zhipu AI$1.28/1MGLM OCRZhipu AI$0.028/1MGLM-4.7-FlashZhipu AI$0.40/1MGLM-5.1Zhipu AI$1.44/1MGLM 5.3 FlashxZhipu AI$0.987/1MGLM-4.7Zhipu AI$1.10/1MGLM-5.2 FAQ
Zhipu AI charges $4.40 /1M for GLM-5.2. The lowest price across providers is $1.80 /1M, at FastRouter.
FastRouter, at $1.80 /1M. 44 providers serve GLM-5.2; the table above lists every one with its price.
GLM-5.2 reads up to 1M tokens per request and writes up to 128K.
Yes. GLM-5.2's weights can be downloaded from its maker's Hugging Face page, under the MIT license.
About 753B, as the safetensors metadata of its official Hugging Face repo states.
44 API providers serve GLM-5.2. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us