TopxAI · Model prices · Zhipu AI (private deployment)
GLM-5.3-Abliterated API pricing
Model id GLM-5.3-Abliterated. $4 input / $7 output per 1M tokens on the lowest-priced route; every route is listed below. Prices are fixed in USD, charged from prepaid credit, and every request writes one usage-log row with the route and the charge.
GLM-5.3-Abliterated: a commercially fine-tuned variant of Z.ai's GLM-5.3 served from a private deployment, not the provider's official API. The tuning adds vertical business skills and removes the built-in refusal alignment (abliterated). Priced above the Z.ai list price of the base model.
Prices by route
| Route | Input (USD / 1M tokens) | Output (USD / 1M tokens) | Cache read (USD / 1M tokens) | Cache write (USD / 1M tokens) | Cache write (1h) (USD / 1M tokens) |
|---|
| Provider list price of GLM-5.3 (checked 2026-09-18) | $1.4 | $4.4 | $0.26 | — | — |
| Private deployment | $4 | $7 | $0.4 | $4 | $4 |
Input, output and cache lanes bill per million tokens. A whole-request long-context row applies once the input context of a request reaches the threshold shown. An Auto-route key sends each request to the lowest-priced route that serves the model.
Notice. Because fine-tuning may affect safety alignment, the model may produce biased, offensive or locally unlawful content. Users bear full responsibility for compliance and legal consequences.
Endpoints
POST /v1/chat/completions: OpenAI Chat Completions (Bearer)
Call GLM-5.3-Abliterated
Base URL https://ai.topxea.com/v1 for OpenAI-style SDKs, https://ai.topxea.com for the Anthropic SDK; the API key goes where the provider's key would go.
curl https://ai.topxea.com/v1/chat/completions \
-H "Authorization: Bearer $TOPXAI_API_KEY" \
-H "content-type: application/json" \
-d '{"model": "GLM-5.3-Abliterated", "messages": [{"role": "user", "content": "Say hello in one sentence."}]}'
Related
Get an API key · Docs · Blog · About TopxAI