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

How do I use Qwen 4 Max in Codex CLI?

qwen/qwen4-max

Codex CLI reaches Qwen 4 Max through the Responses API of MartLLM. In ~/.codex/config.toml, add a model provider with base_url set to https://api.martllm.com/v1 and wire_api = "responses", put your MartLLM key in the UBERLLM_API_KEY environment variable, and set model to qwen/qwen4-max. model_context_window is set to 1,000,000, the context size of Qwen 4 Max, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "qwen/qwen4-max"
model_provider = "uberllm"
model_context_window = 1000000
web_search = "disabled"

[model_providers.uberllm]
name = "MartLLM"
base_url = "https://api.martllm.com/v1"
env_key = "UBERLLM_API_KEY"
wire_api = "responses"

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

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

By API, Qwen 4 Max answers on three addresses with the same MartLLM key and the model id qwen/qwen4-max: OpenAI chat completions at https://api.martllm.com/v1/chat/completions, the OpenAI Responses API at https://api.martllm.com/v1/responses and the Anthropic Messages API at https://api.martllm.com/v1/messages.

How much does the Qwen 4 Max API cost?

On November 20, 2026, Qwen 4 Max costs $0.1353 per million input tokens and $0.4059 per million output tokens through MartLLM, 90.5% below its list price of $1.425 and $4.275. 49 sellers on the market can serve it. In the 7 days before, half of its 1,075 streamed requests got their first token within 6.6 seconds, with a typical prompt of 107,247 tokens. It reads up to 1,000,000 tokens of context. MartLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 11:00 UTC.

Qwen 4 Max in other tools

Other models in Codex CLI