LiteLLMModels

Gemma 3 12B API Pricing

As of October 10, 2026, Gemma 3 12B costs $0.15 per 1M input tokens and $0.50 per 1M output tokens on Databricks, with cache reads at $0.15 and cache writes at $0.15 per 1M tokens. It has a 128,000-token context window and returns up to 32,000 tokens per response.

By GoogleModel ID databricks/databricks-gemma-3-12bPrices updated Checked
Input
$0.15 / 1M tokens
Output
$0.50 / 1M tokens
Cache read
$0.15 / 1M tokens
Context window
128,000 tokens
Max output
32,000 tokens
Providers
1
Added to LiteLLM
December 2025

Gemma 3 12B 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.

ProviderModel name in LiteLLMInputOutputCache readCache writeContext
Databricksdatabricks/databricks-gemma-3-12b$0.15$0.50$0.15$0.15128K

What Gemma 3 12B costs in practice

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

Databricks$0.55

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

Databricks$1.60

Use Gemma 3 12B with LiteLLM

Call Gemma 3 12B 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/databricks-gemma-3-12b",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: gemma-3-12b
    litellm_params:
      model: databricks/databricks-gemma-3-12b
      # 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 sk-1234" \
  -d '{
    "model": "gemma-3-12b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gemma 3 12B FAQ

How much does Gemma 3 12B cost?

Gemma 3 12B costs $0.15 per 1M input tokens and $0.50 per 1M output tokens on Databricks, with cache reads at $0.15 and cache writes at $0.15 per 1M tokens.

What is the context window of Gemma 3 12B?

Gemma 3 12B has a 128,000-token context window and returns up to 32,000 tokens per response.

Which providers offer Gemma 3 12B?

Gemma 3 12B is available from Databricks through LiteLLM, using the model name databricks/databricks-gemma-3-12b.

How do I call Gemma 3 12B with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="databricks/databricks-gemma-3-12b", 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.

When did LiteLLM add Gemma 3 12B?

Gemma 3 12B was added to LiteLLM's model price file in December 2025.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Databricks.

Provider pages: Databricks.