Z.ai (GLM) models, priced in toman
21 Z.ai (GLM) models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Z.ai (GLM) on uttapen
Z.ai (GLM) currently has 21 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Z.ai (GLM) alone is wide: GLM Flash Latest runs about 54 toman for a 1,000-word request, while GLM 5.3 Prime costs 5,221 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Z.ai (GLM) output price undercuts about 52% of the other paid models.
On capabilities: 8 take image input, 21 support tool calling, 21 do multi-step reasoning. The longest context belongs to GLM 5.3 FlashX Legal, at 1,048,576 tokens.
Every Z.ai (GLM) model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which Z.ai (GLM) model should I start with?
Every Z.ai (GLM) model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
GLM 4.5z-ai/glm-4.5 | Tool callingReasoningJSON output | 131,072 | 207,732 | 761,683 |
GLM 4.5 Airz-ai/glm-4.5-air | Tool callingReasoning | 131,072 | 45,009 | 294,286 |
GLM 4.5Vz-ai/glm-4.5v | Image inputTool callingReasoningJSON output | 65,536 | 207,732 | 623,195 |
GLM 4.6z-ai/glm-4.6 | Tool callingReasoningJSON output | 204,800 | 173,110 | 692,439 |
GLM 4.6Vz-ai/glm-4.6v | Image inputTool callingReasoningJSON output | 131,072 | 103,866 | 311,597 |
GLM 4.7z-ai/glm-4.7 | Tool callingReasoningJSON output | 204,800 | 207,732 | 761,683 |
GLM 4.7 Flashz-ai/glm-4.7-flash | Tool callingReasoningJSON output | 200,000 | 20,946 | 138,488 |
GLM 5z-ai/glm-5 | Tool callingReasoningJSON output | 204,800 | 346,219 | 1,107,902 |
GLM 5 Turboz-ai/glm-5-turbo | Tool callingReasoningJSON output | 202,752 | 415,463 | 1,384,877 |
GLM 5.1z-ai/glm-5.1 | Tool callingReasoningJSON output | 204,800 | 484,707 | 1,523,365 |
GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal | Image inputTool callingReasoningJSON output | 1,048,576 | 128,101 | 432,774 |
GLM 5.3 Primez-ai/glm-5.3-prime | Tool callingReasoningJSON output | 1,000,000 | 969,414 | 3,046,730 |
GLM 5.3 FlashXz-ai/glm-5.3-flashx | Image inputTool callingReasoningJSON output | 1,048,576 | 128,101 | 432,774 |
GLM 5.3 Flashz-ai/glm-5.3-flash | Image inputTool callingReasoningJSON output | 1,048,576 | 51,933 | 173,110 |
GLM 5.3z-ai/glm-5.3 | Tool callingReasoningJSON output | 1,048,576 | 24,201 | 484,707 |
GLM 5.2z-ai/glm-5.2 | Tool callingReasoningJSON output | 1,048,576 | 2,077 | 2,354,292 |
GLM 5V Turboz-ai/glm-5v-turbo | Image inputTool callingReasoningJSON output | 202,752 | 415,463 | 1,384,877 |
GLM FlashLatest~z-ai/glm-flash-latest | Image inputTool callingReasoningJSON output | 1,048,576 | 9,867 | 31,956 |
GLM 5.3 FlashBatchz-ai/glm-5.3-flash:batch | Image inputTool callingReasoningJSON output | 1,048,576 | 17,311 | 62,319 |
GLMLatest~z-ai/glm-latest | Tool callingReasoningJSON output | 1,048,576 | 24,201 | 484,707 |
GLM 5.3Batchz-ai/glm-5.3:batch | Tool callingReasoningJSON output | 1,048,576 | 155,799 | 692,439 |
Common questions about the Z.ai (GLM) API
- How do I reach the Z.ai (GLM) API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the Z.ai (GLM) model id. No international card, no VPN. - What do Z.ai (GLM) models cost in toman?
- It depends on the model: the cheapest, GLM Flash Latest, is about 54 toman for a 1,000-word request, and the dearest, GLM 5.3 Prime, about 5,221 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Z.ai (GLM) models are on uttapen?
- 21. 21 support tool calling and 8 accept image input. The catalogue re-syncs hourly, so a newly released model shows up here on its own.