Skip to content
gemini-4-hydrogenChatExamples verified 2026-09-25

Gemini 4 Hydrogen

Fast Gemini 4 generation chat model with 1M context; thinking levels low / medium / high (xhigh is not supported yet). Official price $1.5 / $7.5 (cache read $0.075).

Official price
$1.50 / $7.50/ 1M tokensInput / output
Context window
1M tokens1,048,576
Notes
  • Thinking is on by default and can't be fully turned off; a small max_tokens can leave only thinking and no answer.
  • The Gemini Official Direct (Enterprise) group also supports the Gemini native protocol (POST /v1beta/models/{model}:generateContent, with x-goog-api-key auth); Gemini Value (AI Studio / Vertex) does not.

Pricing

Official price in USD. Actual charge = official price × group multiplier.

Input
$1.50 / 1M tokens
Cached input
$0.075 / 1M tokens
Output
$7.50 / 1M tokens

Endpoints

Same family

Prices come from the public catalog; limits come from specs exported from the gateway’s validation code. Actual charge = official price × group multiplier.