Gemini 4 Hydrogen
Gemini 4 Hydrogen is Google’s fast, efficient model for coding and agentic work, with a unified 1M token context window and tunable thinking.
Input / output
$1.88 / $9.38
per 1M tokens
Context
1M
64K max output
Reasoning
On
fixed effort
Cached input
$0.0938
95% off input
Modalities
Text, image, video, audio
out: text
Pricing
USD per 1M tokensInput
$1.88
Cached input
$0.0938
Output incl. reasoning
$9.38
| Similar models | Input | Output |
|---|---|---|
| Gemini 4 Hydrogen | $1.88 | $9.38 |
| Kimi K3.1 Pro | $2.00 | $10.00 |
| GPT-6.1 Sol | $2.00 | $10.00 |
| Qwen 3.8 2.4T | $2.50 | $7.50 |
| Abliterated Large V2 | $3.00 | $5.00 |
Prompt caching is automatic; see Prompt caching.
Specs
- Model ID
gemini-4-hydrogen- Endpoint
POST /api/v1/chat/completions- Context window
- 1,000,000 tokens
- Max output
- 65,536 tokens
- Reasoning effort
- On at a fixed effort; send
to turn it off where the model allows · guide"reasoning": {"enabled": false } - Served precision
- Set by the upstream provider
- Added
- Nov 14, 2026
Capabilities
Modalities
- Text
- Input and output
- Image
- Input only · up to 1
- Audio
- Input only
- Video
- Input only
Features
- Streaming (SSE)
- Supported
- Function calling
- Supported
- Structured output (json_schema)
- Supported
- Reasoning effort
- Not adjustable
- Prompt caching
- Supported
- Web search
- venice_parameters
- X search
- Not supported
- Log probabilities
- Not supported
- Fine-tuning
- Not supported
- Image generation
- Not supported
POST
/api/v1/chat/completionsRecommendedcurl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'Privacy
Tier 1 · this model
Anonymized
Venice hides your identity and stores no prompts. Google still sees the content.
Tier 2
Private
Not available
Tier 3
TEE
Not available
Tier 4
End-to-end encrypted
Not available