Skip to content

Gemini 4 Hydrogen

ReasoningGoogle

Gemini model for everyday work and tool use through the native Gemini API.

Input
$3.60
per 1M tokens
Output
$18.00
per 1M tokens
Context window
1M
tokens
Max output
32K
tokens

Pricing

Prices are in USD per 1M tokens. Cached input is billed at the cache read price.

Input
$3.60/ 1M
Output
$18.00/ 1M
Cache read
$0.18/ 1M
Audio input
$3.60/ 1M

Use it from code

The samples read your key from the ORYNX_API_KEY environment variable.

Gemini
curl "https://api.orynx.dev/v1beta/models/gemini-4-hydrogen:generateContent" \
  -H "x-goog-api-key: $ORYNX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Explain what an API gateway does in one sentence."}]}]
  }'
gemini-3.8-flash

Google's most intelligent Flash model, with an automatic thinking budget.

Input
$1.80/ 1M
Output
$9.00/ 1M
Gemini1M ctx
OperationalGemini family95.8%Details
gemini-3-flash

High-speed thinking model for agentic work.

Input
$0.115/ 1M
Output
$0.69/ 1M
Gemini1M ctx
OperationalGemini family95.8%Details