Gemini 4 Hydrogen - Unifically

Gemini 4 Hydrogen is Google’s fast Gemini 4 model for everyday coding and agent work, released on November 12, 2026. It accepts text and image input with a 1M-token window shared by input and output, and returns up to 64K output tokens per response. Reasoning effort is tunable with reasoning_effort set to low, medium, high, or xhigh. Thinking tokens are billed as output tokens. A reply at xhigh can take a minute or more to start, so stream the response and set client timeouts with headroom. Try it in the browser: Gemini 4 Hydrogen API playground.

Model

google/gemini-4-hydrogen


Provider	Google
Name	Gemini 4 Hydrogen

Supported Endpoints

Chat Completions — POST /v1/chat/completions

Send LLM requests to https://direct-api.unifically.com, not https://api.unifically.com. The main host sits behind Cloudflare, and Cloudflare’s proxy timeout cuts most LLM requests short before the model has finished writing. When that happens you receive a truncated reply and are still charged for every token generated up to the cut-off. direct-api.unifically.com reaches the same API without the Cloudflare proxy, so long responses complete in full.

Example

curl -X POST https://direct-api.unifically.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemini-4-hydrogen",
    "reasoning_effort": "high",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Find the bug in this function, explain it in two sentences, and write the fix."}
    ]
  }'

Reasoning Effort

Value	When to use it
`low`	Quick steps: classification, extraction, short summaries
`medium`	Routine coding and tool calls
`high`	Multi-step agent work and harder coding tasks
`xhigh`	The hardest reasoning. Slowest to start and uses the most output tokens

Image Input

Send an image in an image_url content part alongside your text, either as a direct https link or inline as a base64 data URI.

curl -X POST https://direct-api.unifically.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemini-4-hydrogen",
    "messages": [
      {"role": "user", "content": [
        {"type": "text", "text": "Read every number in this chart and return them as a JSON table."},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}}
      ]}
    ]
  }'


Accepted shape	`image_url` part with a direct https link or a `data:image/...;base64` URI
Links	Must point straight at the image file, with no redirect, up to 14 MB. A link that cannot be downloaded returns `400` with the reason
Billing	Counted as input tokens at the model’s input rate. The `usage.prompt_tokens` field shows the total

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.