opencheap.si
Credits

Google: Gemini 4 Hydrogen

Gemini 4 Hydrogen is a language model from Google. It reads and writes text.

Price per 1M tokens
$0.20 / $1.01input / output
Cached input
$0.01per 1M tokens
Context
1M tokens943K max output

Providers

8 providers ·

  • 1M context · 524K max output

    • Route 11M context · 943K max outputCache $0.039 · 2.02 s · 186 tok/s · 100 %$0.79 in$3.94 out
    • Route 21M context · 65K max outputCache $0.079 · 1.84 s · 139 tok/s · 95.3 %$1.57 in$7.88 out
    • Route 31M context · 943K max outputCache $0.14 · 1.51 s · 164 tok/s · 100 %$2.83 in$14.18 out
  • 1M context · 524K max output

  • 1M context · 65K max output

  • 1M context · 65K max output

    • Route 11M context · 943K max outputCache $0.079 · 1.59 s · 151 tok/s · 100 %$1.57 in$7.88 out
    • Route 21M context · 65K max outputCache $0.087 · 1.49 s · 136 tok/s · 100 %$1.73 in$8.66 out
    • Route 31M context · 65K max outputCache $0.087 · 5.53 s · 136 tok/s · 100 %$1.73 in$8.66 out
    • Route 41M context · 943K max outputCache $0.14 · 2.25 s · 83 tok/s · 100 %$2.83 in$14.18 out
  • 1 more provider through partner hosts · from $1.57 in · $7.86 out

A request picks by price (:floor) or by speed (provider.sort, :nitro), or sets a floor on tokens per second. How routing works

Price history

No provider selected
Loading…

API

curl https://api.opencheap.si/v1/chat/completions \
  -H "Authorization: Bearer $OPENCHEAP_API_KEY" -H "Content-Type: application/json" \
  -d '{ "model": "opencheap/gemini-4-hydrogen", "messages": [{ "role": "user", "content": "Hi" }] }'