Gemma 3 27B IT API Pricing
As of October 10, 2026, Gemma 3 27B IT is free to use on Google AI Studio. Across 6 providers on LiteLLM, the input price ranges from $0 to $0.90. It has a 131,072-token context window and returns up to 8,192 tokens per response.
- Price
- Free
- Per 1M characters
- $0
- Context window
- 131,072 tokens
- Max output
- 8,192 tokens
- Providers
- 6
- Added to LiteLLM
- March 2025
Gemma 3 27B IT pricing by provider
6 listings across 6 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Per 1M chars | Input | Output | Context |
|---|---|---|---|---|---|
| Google AI Studio | gemini/gemma-3-27b-it | $0 | $0 | $0 | 128K |
| Amazon Bedrock | google.gemma-3-27b-it | – | $0.23 | $0.38 | 128K |
| DeepInfra | deepinfra/google/gemma-3-27b-it | – | $0.08 | $0.16 | 128K |
| Fireworks AI | fireworks_ai/accounts/fireworks/models/gemma-3-27b-it | – | $0.90 | $0.90 | 128K |
| Nebius AI Studio | nebius/google/gemma-3-27b-it | – | $0.10 | $0.30 | 110K |
| Novita AI | novita/google/gemma-3-27b-it | – | $0.119 | $0.20 | 96K |
Other Gemma 3 27B IT prices on Google AI Studio
| Input above 128K tokens | $0 per 1M tokens |
| Output above 128K tokens | $0 per 1M tokens |
| Input image | $0 per image |
What Gemma 3 27B IT costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| Google AI Studio | $0 |
| DeepInfra | $0.24 |
| Nebius AI Studio | $0.35 |
| Novita AI | $0.338 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| Google AI Studio | $0 |
| DeepInfra | $0.832 |
| Nebius AI Studio | $1.06 |
| Novita AI | $1.23 |
Gemma 3 27B IT features
- Function calling
- Structured output
- Image input
- Audio output
Use Gemma 3 27B IT with LiteLLM
Call Gemma 3 27B IT 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.
from litellm import completion
response = completion(
model="gemini/gemma-3-27b-it",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gemma-3-27b-it
litellm_params:
model: gemini/gemma-3-27b-it
api_key: os.environ/GEMINI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gemma-3-27b-it",
"messages": [{"role": "user", "content": "Hello!"}]
}'Gemma 3 27B IT FAQ
How much does Gemma 3 27B IT cost?
Gemma 3 27B IT is free to use on Google AI Studio. Above 128K input tokens, input costs $0 and output costs $0 per 1M tokens. Across 6 providers on LiteLLM, the input price ranges from $0 to $0.90.
What is the context window of Gemma 3 27B IT?
Gemma 3 27B IT has a 131,072-token context window and returns up to 8,192 tokens per response.
Which providers offer Gemma 3 27B IT?
Gemma 3 27B IT is available from 6 providers through LiteLLM: Google AI Studio, Amazon Bedrock, DeepInfra, Fireworks AI, Nebius AI Studio and Novita AI. The lowest price is on Google AI Studio.
How do I call Gemma 3 27B IT with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gemini/gemma-3-27b-it", 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 Gemma 3 27B IT support?
Gemma 3 27B IT supports function calling, structured output and image input. It does not support audio output.
When did LiteLLM add Gemma 3 27B IT?
Gemma 3 27B IT was added to LiteLLM's model price file in March 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:
- aistudio.google.com
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-google-gemma-3-27b-pt.html
- deepinfra.com/pricing
- tokenfactory.nebius.com/models/catalog/text2text/google%2Fgemma-3-27b-it
LiteLLM docs: Google AI Studio, Amazon Bedrock, DeepInfra, Fireworks AI, Nebius AI Studio.
Provider pages: Google AI Studio, Amazon Bedrock, DeepInfra, Fireworks AI, Nebius AI Studio, Novita AI.
