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

How do I use Google: Gemini 4 Argon in Claude Code?

google/gemini-4-argon

Claude Code reaches Google: Gemini 4 Argon through the Anthropic-compatible address of UberLLM. Set ANTHROPIC_BASE_URL to https://api.uberllm.dev (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your UberLLM key and ANTHROPIC_MODEL to google/gemini-4-argon[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to google/gemini-4-argon as well: a slot left unset keeps asking for a Claude model at Claude prices. The [1m] at the end of the id tells Claude Code that Google: Gemini 4 Argon has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.uberllm.dev
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='google/gemini-4-argon[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='google/gemini-4-argon'
export ANTHROPIC_DEFAULT_SONNET_MODEL='google/gemini-4-argon'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='google/gemini-4-argon'
export CLAUDE_CODE_SUBAGENT_MODEL='google/gemini-4-argon'
claude

Claude Code calls: Anthropic Messages API https://api.uberllm.dev/v1/messages · Full Claude Code guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, Google: Gemini 4 Argon answers on three addresses with the same UberLLM key and the model id google/gemini-4-argon: 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 Google: Gemini 4 Argon API cost?

On November 19, 2026, Google: Gemini 4 Argon costs $0.1679 per million input tokens and $0.8396 per million output tokens through UberLLM, 91.6% below its list price of $2.00 and $10.00. 43 sellers on the market can serve it. In the 7 days before, half of its 10,832 streamed requests got their first token within 9.8 seconds, with a typical prompt of 73,470 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.

Google: Gemini 4 Argon in other tools

Other models in Claude Code