GLM 5.3 Flash hosted in Japan: japan-glm-5.3-flash API

Z.ai's GLM 5.3 Flash now has a second route on FastMetal whose inference runs inside Japan. The model id is japan-glm-5.3-flash, and it works through the API and in chat.

The existing glm-5.3-flash stays as it is. Both routes serve the same model; what differs is where inference happens. When a project requires processing in Japan, call japan-glm-5.3-flash; otherwise keep glm-5.3-flash. Switching is a change of model name.

Capabilities

• Hosted and run in Japan. Requests are processed on servers inside Japan. In the catalog and the chat it carries a Japan badge, like every other Japan-hosted route.
• 1M-token context, for feeding long documents in one request.
• Image input. We checked it with real images before launch.
• Tool calling and structured output. Function calling (tools) and strict json_schema responses both worked on real requests.
• A reasoning model. It thinks before answering, and those tokens bill as output. Tune the amount with reasoning_effort.

How prompts are retained and whether they are used for training is listed on the model page. Check it before sending sensitive data.

Pricing

Billed per million input and output tokens, with cached input at its own rate. Billing is prepaid, so you can never spend more than you have loaded. Current rates are on the model page and pricing.

Calling it

FastMetal's API is OpenAI-compatible. Set the model to japan-glm-5.3-flash:

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Authorization: Bearer $FASTMETAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "japan-glm-5.3-flash",
    "messages": [
      {"role": "user", "content": "Summarize the five key points of this contract."}
    ]
  }'

Already on glm-5.3-flash? Changing the model name is the whole migration. To try it without code, pick the Japan-hosted GLM 5.3 Flash in chat.

Before you build on it

• auto never picks it. It is not a candidate for model: "auto"; it serves only requests that name it.
• Expect an occasional 429 at busy times. Japan-hosted capacity is limited, and when it is full the route returns 429. Retry after a short wait.

Real answers from the same model to our shared prompts are on the GLM 5.3 Flash model page. For the other Japan-hosted models, look for the Japan badge in the model catalog.