Aller au contenu principal
Velqa

GLM-4.7 Flash API — pricing and access

Version légère et économique de GLM-4.7

Input
$0.071 USD / 1M tokens
Output
$0.470 USD / 1M tokens
Context
200k
Available on
Starter and above
Provider
Zhipu AI

See plans and prices in USD

Try GLM-4.7 Flash in the playground

GLM-4.7 Flash is the economy version of GLM-4.7: same family, same solid handling of French and Arabic, but a much lower price per token. Available from Starter, it's built for high-traffic assistants — support, FAQs, triaging inbound messages — where conversation volume matters more than the polish of any single answer. Its 200k window is actually wider than GLM-4.7's own, which lets it take in large documents without chunking.

Against GLM-4.7, the full version of the family, Flash loses ground on multi-step reasoning and long, nuanced answers. Against DeepSeek V4 Flash, its direct competitor in the same price bracket, GLM-4.7 Flash keeps the edge on context size, useful for document search.

It is not the right choice when an answer needs to be argued or technical: for that, GLM-4.7 or GLM-5.2 hold up better, at the cost of a higher price per conversation.

Measured on Velqa

Time to first token
0.65 s
Throughput
85.6 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-flash",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Related models

FAQ

How much does GLM-4.7 Flash cost on Velqa?
GLM-4.7 Flash costs $0.071 per million input tokens and $0.470 per million output tokens, in USD. It is included from the Starter plan up.
Can I use GLM-4.7 Flash without a subscription?
Yes. GLM-4.7 Flash 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 Flash compatible with the OpenAI API?
Yes. Point your client at https://api.velqa.dev/v1 and set the model to "glm-4.7-flash" — GLM-4.7 Flash answers on the standard chat completions endpoint, streaming included.