Gemini 4 Hydrogen

google/gemini-4-hydrogen

Maker: Google, United States
Released: 2026-11-12
Knowledge cutoff: 2026-03
Family: gemini
Weights: closed
Tasks: text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering: Experiential Labs, about $0.00375 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Experiential Labs	`gemini-4-hydrogen`	ga	Input: $1.5 Output: $7.5 Cache read: $0.075 Cache write (5 min): $1.5 Cache write (1 h): $1.5 Since 2026-11-13	none	Context: 1,048,576 tokens Max output: 65,536 tokens	`tools` claimed `structured_output` claimed `reasoning` claimed `input.image` claimed
Google Gemini API	`gemini-4-hydrogen`	ga	Input: $1.5 Output: $7.5 Cache read: $0.075 Audio input: $1.5 Since 2026-11-13 · models.dev, MIT	none	Context: 1,048,576 tokens Max input: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` native `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed `web_search` claimed `computer_use` claimed `no_training` claimed
OpenRouter	`google/gemini-4-hydrogen`	ga	Input: $1.5 Output: $7.5 Cache read: $0.075 Cache write (5 min): $0.083333333 Reasoning: $7.5 Audio input: $1.5 Image input tokens: $1.5 Since 2026-11-13	none	Context: 1,048,576 tokens Max output: 943,718 tokens	`input.text` claimed `input.image` claimed `input.pdf` native `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`google/gemini-4-hydrogen:batch`	ga	Input: unknown Output: unknown Input, batch tier: $0.75 Output, batch tier: $3.75 Cache read, batch tier: $0.0375 Cache write (5 min), batch tier: $0.083333333 Reasoning, batch tier: $3.75 Audio input, batch tier: $0.75 Image input tokens, batch tier: $0.75 Since 2026-11-13	none	Context: 1,048,576 tokens Max output: 943,718 tokens	`input.text` claimed `input.image` claimed `input.audio` claimed `input.video` claimed `input.pdf` native `output.text` claimed `tools` claimed `tool_choice` claimed `structured_output` claimed `reasoning` claimed `prompt_caching` claimed
Google Vertex AI	`gemini-4-hydrogen`	ga	Input: $1.5 Output: $7.5 Cache read: $0.075 Audio input: $1.5 Since 2026-11-13 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 65,536 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `input.audio` claimed `input.video` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed `web_search` claimed `computer_use` claimed `no_training` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`lmarena:text_style_control`	0.897	1490.4275	2026-11-11	LMArena, CC-BY-4.0, normalized by Nanner Tech
`lmarena:webdev`	0.633	1704.2133	2026-11-11	LMArena, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

gemini-4-hydrogen
google/gemini-4-hydrogen:batch
~google/gemini-flash-latest

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/google/gemini-4-hydrogen' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=experiential,gemini,openrouter,vertex' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-13.1 of 2026-11-13. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).