How much does GLM-4.7 cost on Velqa?

GLM-4.7 costs $0.470 per million input tokens and $2.056 per million output tokens, in USD. It is included from the Starter plan up.

Can I use GLM-4.7 without a subscription?

Yes. GLM-4.7 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-4.7 compatible with the OpenAI API?

Yes. Point your client at https://api.velqa.dev/v1 and set the model to "glm-4.7" — GLM-4.7 answers on the standard chat completions endpoint, streaming included.

GLM-4.7 API — pricing and access

Chat général, bon en FR / AR / ZH

Input: $0.470 USD / 1M tokens
Output: $2.056 USD / 1M tokens
Context: 128k
Available on: Starter and above
Provider: Zhipu AI

GLM-4.7 is the conversation model we put in every plan, including Starter. It's the default choice for dialogue, drafting, or answering questions over a document set: it handles French and Arabic well, which is not a given at its price point, and its 128k window is enough to hand it a whole file without chunking.

Against GLM-4.7 Flash, the gap shows up on long answers: Flash is cheaper and faster, but slips on multi-step reasoning. If your workload is an agent chaining tool calls, look at Hunyuan Hy3 or MiniMax M3 instead, both built for that. GLM-4.7 is not a coding model: it writes correct functions, but on an existing codebase it loses the thread faster than Kimi K2.6.

In practice we recommend it for a customer-support assistant, document search with citations, or any product where the cost per conversation has to stay predictable.

Measured on Velqa

Time to first token: 0.56 s
Throughput: 59.3 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-4.7",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does GLM-4.7 cost on Velqa?: GLM-4.7 costs $0.470 per million input tokens and $2.056 per million output tokens, in USD. It is included from the Starter plan up.
Can I use GLM-4.7 without a subscription?: Yes. GLM-4.7 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-4.7 compatible with the OpenAI API?: Yes. Point your client at https://api.velqa.dev/v1 and set the model to "glm-4.7" — GLM-4.7 answers on the standard chat completions endpoint, streaming included.