How do I use DeepSeek V3.2 in Codex CLI?
deepseek/deepseek-v3.2Codex CLI reaches DeepSeek V3.2 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 deepseek/deepseek-v3.2. model_context_window is set to 160,000, the context size of DeepSeek V3.2, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.
model = "deepseek/deepseek-v3.2"
model_provider = "uberllm"
model_context_window = 160000
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, DeepSeek V3.2 answers on three addresses with the same UberLLM key and the model id deepseek/deepseek-v3.2: 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.