Skip to content
Tokenjoy

Zhipu · Chat

GLM-5.3-Flash API: pricing and access

Call GLM-5.3-Flash through Tokenjoy’s OpenAI-compatible endpoint. Change base_url and the API key to connect, with public prices and billing by actual usage.

Pricing

  • Input: ¥0.8 / 1M tokens
  • Output: ¥2.8 / 1M tokens
  • read ¥0.23 / 1M tokens

Shown here are list prices and the default platform discount. Negotiated company prices and prices of your own channels follow the console and your actual bill.

How to connect

  • Create an API key under “My keys” in the console and enable this model
  • Set the SDK base_url to https://app.tokenjoy.me/v1
  • Use the model name below in the model parameter
curl https://app.tokenjoy.me/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tj-..." \
  -d '{"model":"GLM-5.3-Flash","messages":[{"role":"user","content":"Hello!"}]}'

FAQ

How much does the GLM-5.3-Flash API cost?

Input: ¥0.8 / 1M tokens; Output: ¥2.8 / 1M tokens; read ¥0.23 / 1M tokens

How do I call the GLM-5.3-Flash API?

Set the SDK base_url to https://app.tokenjoy.me/v1, use an API key issued by Tokenjoy, and put GLM-5.3-Flash in the model parameter. What it can do depends on the model and channel.

Further reading

← Back to home