How do I use Gemini 3.8 Flash in Codex CLI?
google/gemini-3.8-flashCodex CLI reaches Gemini 3.8 Flash 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 google/gemini-3.8-flash. model_context_window is set to 1,048,576, the context size of Gemini 3.8 Flash, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.
model = "google/gemini-3.8-flash"
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, Gemini 3.8 Flash answers on three addresses with the same UberLLM key and the model id google/gemini-3.8-flash: 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.