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

How do I use Gemini 3.8 Flash in Codex CLI?

google/gemini-3.8-flash

Codex 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.

toml
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.

How much does the Gemini 3.8 Flash API cost?

On November 19, 2026, Gemini 3.8 Flash costs $0.0664 per million input tokens and $0.3319 per million output tokens through UberLLM, 92% below its list price of $0.825 and $4.125. 123 sellers on the market can serve it. In the 7 days before, half of its 46,992 streamed requests got their first token within 3.5 seconds, with a typical prompt of 45,815 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.

Gemini 3.8 Flash in other tools

Other models in Codex CLI