impulse

System AI Gemini 4 Hydrogen

API id system.ai.gemini-4-hydrogen
Input / 1M
$1.50
at Databricks
Output / 1M
$7.50
at Databricks
Context window
1M
tokens
Max output
66K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Databricks, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$1.50$7.50
Cached input$1.50
Cache write, 5 minutes$1.50

What it costs a month

At Databricks list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$1,013
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$990
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$2,250
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$5,400
Use your own numbers

Where to run it

1 host serve System AI Gemini 4 Hydrogen. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
system.ai.gemini-4-hydrogen
$1.50 / $7.50

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Databricks.

Smaller Independent models

No cheaper Independent model keeps its key capabilities.

Other frontier labs

  • GPT-6.1 Terra
    OpenAI · on OpenAI
    $1.00 / $5.00
    Has every key capability
    33% less
  • Grok 4.20 Multi Agent
    xAI · on xAI
    $1.25 / $2.50
    Has every key capability
    48% less
  • Gemini 3.8 Flash
    Google · on Google AI Studio
    $0.75 / $3.75
    Has every key capability
    50% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    93% less

Open-weight picks

  • Qwen4 Max
    Alibaba Qwen · on Alibaba DashScope
    $1.50 / $4.50
    Has every key capability
    25% less
  • Muse Spark Open
    Meta · on Baseten
    $1.25 / $4.25
    Has every key capability
    33% less
  • Inkling
    Independent · on DeepInfra
    $0.95 / $4.05
    Has every key capability
    43% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    71% less

Call it

Using Databricks's API.

Python
from litellm import completion

response = completion(
    model="databricks/system.ai.gemini-4-hydrogen",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does System AI Gemini 4 Hydrogen cost?

On Databricks, System AI Gemini 4 Hydrogen costs $1.50 per million input tokens and $7.50 per million output tokens. Cached input costs $1.50 per million tokens.

Which APIs offer System AI Gemini 4 Hydrogen?

System AI Gemini 4 Hydrogen runs on 1 API: Databricks.

What is System AI Gemini 4 Hydrogen's context window?

1M tokens, with up to 66K tokens in one reply.

Is System AI Gemini 4 Hydrogen being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to System AI Gemini 4 Hydrogen?

Models that cost less and keep most of what it can do: GPT-6.1 Terra on OpenAI (33% less), Grok 4.20 Multi Agent on xAI (48% less) and Qwen4 Max on Alibaba DashScope (25% less). Savings are on a mix of 3 input tokens to 1 output token.

What is System AI Gemini 4 Hydrogen's API model id?

Use system.ai.gemini-4-hydrogen with Databricks.

Sources

Raw catalog entry for system.ai.gemini-4-hydrogen on Databricks
{
  "cache_creation_input_token_cost": 0.0000015,
  "cache_read_input_token_cost": 0.0000015,
  "input_cost_per_token": 0.0000015,
  "litellm_provider": "databricks",
  "max_input_tokens": 1048576,
  "max_output_tokens": 65536,
  "metadata": {
    "notes": "Gemini 4 Hydrogen on Databricks is available only through Unity Gateway with the model service name system.ai.gemini-4-hydrogen on a global endpoint, and Databricks supports text input only. The Databricks pricing pages list no row for it yet, so input and output are the Global rates on the Vertex AI pricing page for Gemini 4 Hydrogen, no '*_dbu_cost_per_token' fields are published, and cache tokens bill at the input rate until Databricks publishes cache DBU rates."
  },
  "mode": "chat",
  "output_cost_per_token": 0.0000075,
  "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models",
  "supported_modalities": [
    "text"
  ],
  "supported_output_modalities": [
    "text"
  ],
  "supports_audio_input": false,
  "supports_reasoning": true,
  "supports_video_input": false,
  "supports_vision": false
}