Skip to main content
Watch: I Built an AI App Without Leaving Databricks

API compatibility - 2 documented limits

Z.ai (GLM) API compatibility

Z.ai documents an OpenAI-compatible API at https://api.z.ai/api/paas/v4/ (chat/completions and responses). Its Anthropic-compatible base URL, the value for ANTHROPIC_BASE_URL, is https://api.z.ai/api/anthropic. The docs list 2 limitations: 2 for the OpenAI-compatible layer.

Verified against Z.ai's own documentation. Not documented means the docs read that day do not say; it never means No.

Compare every provider in the API compatibility matrix.

OpenAI-compatible API

Supported
Base URL
https://api.z.ai/api/paas/v4/
Endpoints
  • chat/completions
  • responses
Auth
Authorization: Bearer ZAI_API_KEY
Notes
General (pay-as-you-go) endpoint is https://api.z.ai/api/paas/v4. GLM Coding Plan subscribers must use dedicated endpoints instead: OpenAI Chat Completions at https://api.z.ai/api/coding/paas/v4 and OpenAI Responses at https://api.z.ai/api/v1 (the Responses endpoint is documented only on the Coding Plan page). Thinking is toggled via extra_body {"thinking": {"type": "enabled"}}.

From the docs

Z.AI provides interfaces compatible with OpenAI API, which means you can use existing OpenAI SDK code and seamlessly switch to Z.AI's model services by simply modifying the API key and base URL.
docs.z.ai/guides/develop/openai/python

Anthropic-compatible API

Supported
ANTHROPIC_BASE_URL
https://api.z.ai/api/anthropic
Auth
ANTHROPIC_AUTH_TOKEN
Notes
Documented in the GLM Coding Plan context (Claude Code guide and the Coding Endpoint table). The docs read today do not describe a separate pay-as-you-go Anthropic endpoint.

From the docs

GLM Coding Plan supports both the Anthropic and OpenAI protocols. Make sure to configure the correct Base URL: | Anthropic Messages | https://api.z.ai/api/anthropic | OpenAI Chat Completions | https://api.z.ai/api/coding/paas/v4 | OpenAI Responses | https://api.z.ai/api/v1 |
docs.z.ai/devpack/tool/others

Documented limitations

Parameters, content types and features Z.ai (GLM)'s docs say its compatibility layers ignore, reject or change, each with the line it comes from. A layer with nothing listed may still differ in ways the docs do not spell out.

OpenAI-compatible layer2

  • temperature range (0,1); temperature = 0 (do_sample = False) not applicable via OpenAI calls

    Note: The temperature parameter range is (0,1), do_sample = False (temperature = 0) is not applicable in OpenAI calls.
    docs.z.ai/guides/develop/openai/python

  • general statement of differences

    In some scenarios, there are still differences between Z.AI and OpenAI interfaces, but this does not affect overall compatibility.
    docs.z.ai/guides/develop/openai/python

Anthropic-compatible layer0

No limitations listed in the docs read.

Example from Z.ai (GLM)'s docs

Copied verbatim from the provider's documentation, placeholders included.

Provider example
from openai import OpenAI

client = OpenAI(
    api_key="your-Z.AI-api-key",
    base_url="https://api.z.ai/api/paas/v4/"
)

completion = client.chat.completions.create(
    model="glm-5.3",
    messages=[
        {"role": "system", "content": "You are a smart and creative novelist"},
        {"role": "user", "content": "Please write a short fairy tale story as a fairy tale master"}
    ]
)

More on Z.ai (GLM)

Use Z.ai (GLM) in a coding tool

Newsletter

Know when a provider changes its API

One email per week. New models, new endpoints and the compatibility changes that break a base URL, and what they mean for your stack.