How much does GLM-5.2 cost on Velqa?

GLM-5.2 costs $1.093 per million input tokens and $3.525 per million output tokens, in USD. It is included from the Dev plan up.

Can I use GLM-5.2 without a subscription?

Yes. GLM-5.2 can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.

Is GLM-5.2 compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "glm-5.2" — GLM-5.2 answers on the standard chat completions endpoint, streaming included.

GLM-5.2 API — pricing and access

Nouvelle génération, chat général FR / AR / ZH

Input: $1.093 USD / 1M tokens
Output: $3.525 USD / 1M tokens
Context: 128k
Available on: Dev and above
Provider: Zhipu AI

GLM-5.2 is the new generation of the Zhipu family: the same French / Arabic / Chinese coverage as GLM-4.7, but noticeably better answers on topics that need nuance — content writing, advanced support, summarizing ambiguous documents. It requires the Dev plan or above.

Against GLM-4.7, its predecessor in the same family, GLM-5.2 costs roughly twice as much per token: it makes sense to pick it when writing quality is the criterion, not when the job is running a large volume of simple conversations. Against Kimi K2.6, a Dev-tier neighbor at a very close price, the difference is clear-cut: Kimi targets code and long agentic sessions, GLM-5.2 targets conversation and writing.

It is not the right choice for a high-traffic assistant where cost per message has to stay low: GLM-4.7 or GLM-4.7 Flash cover that case for much less. It also isn't built for an agent chaining tool calls: MiniMax M3 or Hunyuan Hy3 are purpose-built for that.

Measured on Velqa

Time to first token: 0.90 s
Throughput: 40.1 tokens/s

Median of 5 streamed calls against api.velqa.dev, 2026-08-10.

Call it

OpenAI-compatible endpoint — change the base URL and the model id, nothing else.

curl https://api.velqa.dev/v1/chat/completions \
  -H "Authorization: Bearer $VELQA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does GLM-5.2 cost on Velqa?: GLM-5.2 costs $1.093 per million input tokens and $3.525 per million output tokens, in USD. It is included from the Dev plan up.
Can I use GLM-5.2 without a subscription?: Yes. GLM-5.2 can be called with prepaid Boost credit, without a monthly plan. Trying it in the playground does need an account, though: anonymous playground access is limited to the demo model.
Is GLM-5.2 compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "glm-5.2" — GLM-5.2 answers on the standard chat completions endpoint, streaming included.