Z-AI (GLM) API Pricing
Complete pricing for all Z-AI (GLM) models. Input/output costs per 1M tokens, context windows, and rate limits.
Billing terms: priced in USD per 1M tokens unless a row states otherwise; official direct rates are listed separately from third-party channels, and regional prices are kept distinct. Record updated 2026-10-10.
Z-AI (GLM) API Pricing Calculator
Select a model to estimate monthly cost using its listed rates on each channel.
Workloads reusing system prompts, long documents, or conversation history hit more; channels without a cached rate are billed at the full input rate.
| Channel | Effective input | Output /1M | Est. / month |
|---|---|---|---|
| official | $0.36(w/ cache) | $2.20 | $2.47 |
Formula: monthly cost = (input tokens × effective input rate + output tokens × output rate) ÷ 1,000,000 × calls. The effective input rate blends list and cached rates at your cache-hit share. Rates share the selected model and billing basis; your vendor bill is authoritative.
Currently available rates
GLM 5.2 (batch)
LLMz-ai-glm-5.2-batchLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM 5.2 (free)
LLMz-ai-glm-5.2-freeLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM 5.3 (batch)
LLMz-ai-glm-5.3-batchGLM 5.3 Flash (batch)
LLMz-ai-glm-5.3-flash-batchGLM 5.3 Prime
LLMz-ai-glm-5.3-primeGLM Flash Latest
LLMz-ai-glm-flash-latestDeprecated endpoints may still be callable. Migrate before retirement.
GLM Latest
LLMz-ai-glm-latestDeprecated endpoints may still be callable. Migrate before retirement.
GLM-4.5
LLMz-ai-glm-4.5Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-4.5-Air
LLMz-ai-glm-4.5-airGLM-4.5-Flash
LLMz-ai-glm-4.5-flashLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3-flashGLM-4.5V
LLMz-ai-glm-4.5vLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-4.6vGLM-4.6
LLMz-ai-glm-4.6Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-4.6V
LLMz-ai-glm-4.6vGLM-4.6V-Flash
LLMz-ai-glm-4.6v-flashGLM-4.7
LLMz-ai-glm-4.7Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-4.7-Flash
LLMz-ai-glm-4.7-flashLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3-flashGLM-4.7-FlashX
LLMz-ai-glm-4.7-flashxLegacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3-flashxGLM-5
LLMz-ai-glm-5Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-5-Turbo
LLMz-ai-glm-5-turboGLM-5.1
LLMz-ai-glm-5.1Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-5.2
LLMz-ai-glm-5.2Legacy / superseded version. Newer models are available; official or partner channels may still serve this version.
Replacement reference: z-ai-glm-5.3GLM-5.3
LLMz-ai-glm-5.3GLM-5.3-Flash
LLMz-ai-glm-5.3-flashGLM-5.3-FlashX
LLMz-ai-glm-5.3-flashxGLM-5V-Turbo
LLMz-ai-glm-5v-turboDoes this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.