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 Hydrogen in Claude Code?

google/gemini-4-hydrogen

Claude Code reaches Google: Gemini 4 Hydrogen 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-hydrogen[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to google/gemini-4-hydrogen 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 Hydrogen 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-hydrogen[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='google/gemini-4-hydrogen'
export ANTHROPIC_DEFAULT_SONNET_MODEL='google/gemini-4-hydrogen'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='google/gemini-4-hydrogen'
export CLAUDE_CODE_SUBAGENT_MODEL='google/gemini-4-hydrogen'
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 Hydrogen answers on three addresses with the same UberLLM key and the model id google/gemini-4-hydrogen: 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 Hydrogen API cost?

On November 19, 2026, Google: Gemini 4 Hydrogen costs $0.1451 per million input tokens and $0.7253 per million output tokens through UberLLM, 90.3% below its list price of $1.50 and $7.50. 25 sellers on the market can serve it. In the 7 days before, half of its 37,468 streamed requests got their first token within 3.5 seconds, with a typical prompt of 70,170 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 08:00 UTC.

Google: Gemini 4 Hydrogen in other tools

Other models in Claude Code