Gemma 3 27B IT
Gemma 3 introduces multimodality, supporting vision-language input and text outputs.
gemma-3-27b-itReleased 12 Mar 2025 (Mar 2025)Where to run it
6 hosts serve Gemma 3 27B IT. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Google AI StudioLab API gemma-3-27b-it | - | gemma-3-27b-it | |
DeepInfraInference gemma-3-27b-it | $0.08 / $0.16 | gemma-3-27b-it | |
Novita AIInference gemma-3-27b-it | $0.119 / $0.20 | gemma-3-27b-it | |
Nebius AI StudioInference gemma-3-27b-it | $0.10 / $0.30 | gemma-3-27b-it | |
Amazon BedrockCloud google.gemma-3-27b-it | $0.23 / $0.38 Retires 30 Mar 2027 | google.gemma-3-27b-it | Retires 30 Mar 2027 |
Fireworks AIInference gemma-3-27b-it | $0.90 / $0.90 | gemma-3-27b-it |
Show 1 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| Mantle google.gemma-3-27b-it | $0.23 / $0.38 Retires 30 Mar 2027 | google.gemma-3-27b-it | Retires 30 Mar 2027 | ||||
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
- TextImages
- Produces
- Text
- Open weights
- License: Gemma LicenseRuns in about 65.8 GB of GPU memoryRuntimes: Ollama, llama.cpp, vLLM
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller Google models
Other frontier labs
Open-weight picks
Benchmarks
Scores published on the model card.
- Aider Polyglot4.9%
Call it
Using Google AI Studio's API.
from google import genai
client = genai.Client() # reads GEMINI_API_KEY
response = client.models.generate_content(model="gemma-3-27b-it", contents="Hello")
print(response.text)curl "https://generativelanguage.googleapis.com/v1beta/models/gemma-3-27b-it:generateContent" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Hello"}]}]}'from litellm import completion
response = completion(
model="gemini/gemma-3-27b-it",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Gemma 3 27B IT cost?
Its lowest listed price is at DeepInfra: $0.08 per million input tokens and $0.16 per million output tokens.
Which APIs offer Gemma 3 27B IT?
Gemma 3 27B IT runs on 6 APIs: Google AI Studio, DeepInfra, Novita AI, Nebius AI Studio, Amazon Bedrock and Fireworks AI.
What is Gemma 3 27B IT's context window?
131K tokens, with up to 8K tokens in one reply.
Is Gemma 3 27B IT being retired?
Amazon Bedrock retires it on 30 Mar 2027. 5 hosts keep serving it.
When was Gemma 3 27B IT released?
Google released it on 12 Mar 2025.
What is Gemma 3 27B IT's API model id?
Use gemma-3-27b-it with Google AI Studio. Other hosts use their own ids: google.gemma-3-27b-it on Amazon Bedrock.
Sources
- DeepInfra pricing
- Google AI Studio pricing
- Nebius AI Studio pricing
- Amazon Bedrock pricing
- LiteLLM model map
Raw catalog entry for gemma-3-27b-it on Google AI Studio
{
"input_cost_per_audio_per_second": 0,
"input_cost_per_audio_per_second_above_128k_tokens": 0,
"input_cost_per_character": 0,
"input_cost_per_character_above_128k_tokens": 0,
"input_cost_per_image": 0,
"input_cost_per_image_above_128k_tokens": 0,
"input_cost_per_token": 0,
"input_cost_per_token_above_128k_tokens": 0,
"input_cost_per_video_per_second": 0,
"input_cost_per_video_per_second_above_128k_tokens": 0,
"litellm_provider": "gemini",
"max_input_tokens": 131072,
"max_output_tokens": 8192,
"mode": "chat",
"output_cost_per_character": 0,
"output_cost_per_character_above_128k_tokens": 0,
"output_cost_per_token": 0,
"output_cost_per_token_above_128k_tokens": 0,
"source": "https://aistudio.google.com",
"supports_audio_output": false,
"supports_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": false,
"supports_tool_choice": true,
"supports_vision": true
}