Google Gemma 3 27B Instruct
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google’s open source model, successor to Gemma 2.
Last 24 hours of Venice traffic.How it’s measured
Capabilities
What the model takes in, returns and supports through the API.
stream: truetoolsStructured outputsresponse_formatVisionUp to 10 imagesenable_web_searchNot supportedreasoning, video input, audio input, X search, prompt caching and log probabilities
Benchmarks
Specs
- Model ID
google-gemma-3-27b-it- Endpoint
POST /api/v1/chat/completions- Context window
- 198,000 tokens
- Max output
- 16,384 tokens
- Reasoning
- None
- Precision
- FP8
- Privacy
- Private
- Weights
- google/gemma-3-27b-it
- Added
- Nov 4, 2025
Compare
| Model | Input | Output |
|---|---|---|
| Google Gemma 3 27B Instruct | $0.12 | $0.20 |
| OpenAI GPT OSS 120B | $0.07 | $0.30 |
| Mistral Small 3.2 24B Instruct | $0.0938 | $0.25 |
| NVIDIA Nemotron 3 Nano 30B | $0.075 | $0.30 |
| GLM 4.7 Flash Heretic | $0.07 | $0.40 |
Other versions
- Google Gemma 3 27B InstructNov 2025
- Google Gemma 4 31B InstructApr 2026
Pricing
Billed per token in USD. Reasoning tokens bill as output.
Estimate a workload
Blended price against similar models
Quickstart
OpenAI-compatible: point any OpenAI SDK at the Venice base URL with a Venice API key.
curl https://api.venice.ai/api/v1/chat/completions \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google-gemma-3-27b-it",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'https://api.venice.ai/api/v1Parameters
| Parameter | Values |
|---|---|
model | google-gemma-3-27b-it |
messages | text · image_url |
max_completion_tokens | Up to 16,384 |
tools | Function definitions |
response_format | { type: |
stream | true | false |
venice_parameters.enable_web_search | auto | on | off |