baidu-qianfan

GLM 5.3

glm-5.3

baidu-qianfan1.2M context$1.18 / 1M tokens (input)$4.12 / 1M tokens (output)

GLM 5.3 is Z.ai's large-scale reasoning model for complex software engineering and long-horizon agent tasks. It improves on GLM 5.2 in coding capability and performance per token while retaining a million-token-class text context window. Reasoning is always enabled and supports low, high, and max effort levels, with max as the default. The model supports function calling, tool choice, structured JSON outputs, prompt caching, and streaming. This AnyInt deployment is served through Baidu Qianfan with a 1,179,648-token context window and up to 131,072 output tokens.

Chat with GLM 5.3

Total Context1.2M

Input Price$1.18

Output Price$4.12

Providers for GLM 5.3

AnyInt routes requests to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.

baidu-qianfan

Total Context1.2M

Input Price$1.18

Output Price$4.12

Sample code and API for GLM 5.3

AnyInt generates a quickstart from this model's declared API operations, including complete polling flows for asynchronous media.

Create API key

Choose an operation and language that match this model.

ResponsesOpenAI compatible

Call the standard operation supported by this model.

/v1/responses

curl 'https://api.anyint.ai/v1/responses' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -d '{
  "model": "glm-5.3",
  "input": "Describe a calm futuristic city at sunrise."
}'

Popular Models

Explore the most popular AI models, covering text generation, coding, image processing and more