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

How do I use GLM 5.3 in Codex CLI?

z-ai/glm-5.3

Codex CLI reaches GLM 5.3 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-5.3. model_context_window is set to 1,000,000, the context size of GLM 5.3, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "z-ai/glm-5.3"
model_provider = "uberllm"
model_context_window = 1000000
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 5.3 answers on three addresses with the same UberLLM key and the model id z-ai/glm-5.3: 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 5.3 API cost?

On November 19, 2026, GLM 5.3 costs $0.000663 per million input tokens and $0.0133 per million output tokens through UberLLM, 99.7% below its list price of $1.40 and $4.40. 222 sellers on the market can serve it. In the 7 days before, half of its 100,994 streamed requests got their first token within 9.6 seconds, with a typical prompt of 106,995 tokens. It reads up to 1,000,000 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 08:00 UTC.

GLM 5.3 in other tools

Other models in Codex CLI