LiteLLMLiteLLM/ MODELS

Ai.gemini 4 Hydrogen API Pricing

1 providerdatabricks/system.ai.gemini-4-hydrogenCompare
Input / output
$1.875 / $9.375 per 1M tokens
Cache read
$0.09373 / 1M
Context
1M tokens
Max output
64K tokens

As of November 21, 2026, Ai.gemini 4 Hydrogen costs $1.875 per 1M input tokens and $9.375 per 1M output tokens on Databricks, with cache reads at $0.09373 and cache writes at $2.344 per 1M tokens. It has a 1,048,576-token context window and returns up to 65,536 tokens per response.

Prices updated Checked

Ai.gemini 4 Hydrogen pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

Ai.gemini 4 Hydrogen prices by provider in US dollars, token prices per 1M tokens, as of November 21, 2026. Source: LiteLLM model price file.
ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Databricksdatabricks/system.ai.gemini-4-hydrogen$1.875$9.375$0.09373$2.3441M

Other Ai.gemini 4 Hydrogen prices on Databricks

Priority input$3.375 per 1M tokens
Priority output$16.87 per 1M tokens

What Ai.gemini 4 Hydrogen costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Databricks$8.438

100 long-document requests with 100,000 input and 2,000 output tokens each

Databricks$20.63

Ai.gemini 4 Hydrogen cost calculator

At Databricks's price ($1.875 input, $9.375 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $65.63 a day, about $1,969 a month. Change the numbers for your workload, or compare it with other models.

Per request
$0.006563
Per day
$65.63
Per month (30 days)
$1,969

Ai.gemini 4 Hydrogen features

Input: text. Output: text.

Use Ai.gemini 4 Hydrogen with LiteLLM

Call Ai.gemini 4 Hydrogen through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="databricks/system.ai.gemini-4-hydrogen",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: system.ai.gemini-4-hydrogen
    litellm_params:
      model: databricks/system.ai.gemini-4-hydrogen
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "system.ai.gemini-4-hydrogen",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Ai.gemini 4 Hydrogen price history

DatePrice
November 17, 2026$1.50 / $7.50 per 1M tokens
November 20, 2026$1.875 / $9.375 per 1M tokens

Ai.gemini 4 Hydrogen FAQ

How much does Ai.gemini 4 Hydrogen cost?

Ai.gemini 4 Hydrogen costs $1.875 per 1M input tokens and $9.375 per 1M output tokens on Databricks, with cache reads at $0.09373 and cache writes at $2.344 per 1M tokens.

What is the context window of Ai.gemini 4 Hydrogen?

Ai.gemini 4 Hydrogen has a 1,048,576-token context window and returns up to 65,536 tokens per response.

Which providers offer Ai.gemini 4 Hydrogen?

Ai.gemini 4 Hydrogen is available from Databricks through LiteLLM, using the model name databricks/system.ai.gemini-4-hydrogen.

How do I call Ai.gemini 4 Hydrogen with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="databricks/system.ai.gemini-4-hydrogen", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does Ai.gemini 4 Hydrogen support?

Ai.gemini 4 Hydrogen supports reasoning and prompt caching. It does not support image input, audio input and video input.

When did LiteLLM add Ai.gemini 4 Hydrogen?

Ai.gemini 4 Hydrogen was added to LiteLLM's model price file on November 17, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:

LiteLLM docs: Databricks.

Provider pages: Databricks.