NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
glm logo

How do I use GLM-5.2 in Codex CLI?

z-ai/glm-5.2

Codex CLI reaches GLM-5.2 through the Responses API of UberLLM. In ~/.codex/config.toml, add a model provider with base_url set to https://api.uberllm.dev/v1 and wire_api = "responses", put your UberLLM key in the UBERLLM_API_KEY environment variable, and set model to z-ai/glm-5.2. model_context_window is set to 1,048,576, the context size of GLM-5.2, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "z-ai/glm-5.2"
model_provider = "uberllm"
model_context_window = 1048576
web_search = "disabled"

[model_providers.uberllm]
name = "UberLLM"
base_url = "https://api.uberllm.dev/v1"
env_key = "UBERLLM_API_KEY"
wire_api = "responses"

Codex CLI calls: OpenAI Responses API https://api.uberllm.dev/v1/responses · Full Codex CLI guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, GLM-5.2 answers on three addresses with the same UberLLM key and the model id z-ai/glm-5.2: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How much does the GLM-5.2 API cost?

On November 19, 2026, GLM-5.2 costs $0.00075 per million input tokens and $0.00293 per million output tokens through UberLLM, 99.9% below its list price of $1.40 and $4.40. 133 sellers on the market can serve it. In the 7 days before, half of its 3,419 streamed requests got their first token within 4.4 seconds, with a typical prompt of 39,715 tokens. It reads up to 1,048,576 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 09:00 UTC.

GLM-5.2 in other tools

Other models in Codex CLI