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

How do I use GPT-6 Astra in Codex CLI?

openai/gpt-6-astra

Codex CLI reaches GPT-6 Astra 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 openai/gpt-6-astra. model_context_window is set to 1,050,000, the context size of GPT-6 Astra, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "openai/gpt-6-astra"
model_provider = "uberllm"
model_context_window = 1050000
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, GPT-6 Astra answers on three addresses with the same UberLLM key and the model id openai/gpt-6-astra: 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 GPT-6 Astra API cost?

On November 19, 2026, GPT-6 Astra costs $0.2118 per million input tokens and $1.0588 per million output tokens through UberLLM, 97.9% below its list price of $10.00 and $50.00. 91 sellers on the market can serve it. In the 7 days before, half of its 156 streamed requests got their first token within 2.1 seconds, with a typical prompt of 98 tokens. It reads up to 1,050,000 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 09:00 UTC.

GPT-6 Astra in other tools

Other models in Codex CLI