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

How do I use Claude Opus 4.6 in Codex CLI?

anthropic/claude-opus-4.6

Codex CLI reaches Claude Opus 4.6 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 anthropic/claude-opus-4.6. model_context_window is set to 1,000,000, the context size of Claude Opus 4.6, because Codex assumes 272,000 tokens for models outside the list of OpenAI models it knows.

toml
model = "anthropic/claude-opus-4.6"
model_provider = "uberllm"
model_context_window = 1000000
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, Claude Opus 4.6 answers on three addresses with the same UberLLM key and the model id anthropic/claude-opus-4.6: 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 Claude Opus 4.6 API cost?

On November 19, 2026, Claude Opus 4.6 costs $0.3952 per million input tokens and $1.976 per million output tokens through UberLLM, 92.1% below its list price of $5.00 and $25.00. 91 sellers on the market can serve it. In the 7 days before, half of its 1,650 streamed requests got their first token within 2.2 seconds, with a typical prompt of 13,445 tokens. It reads up to 1,000,000 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 09:00 UTC.

Claude Opus 4.6 in other tools

Other models in Codex CLI