google
Google: Gemma 4 31B (free)
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Quality Score
100/100
composite of price, context, capability
Input Price
Free
per 1M tokens
Output Price
Free
per 1M tokens
Context Window
262,144
tokens
- Model ID
- google/gemma-4-31b-it:free
- Vendor
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Strong choice for
Code
Regex Writing
Crafting regular expressions that actually match what you intend.
Code
Frontend Component Design
Generating React/Vue/Svelte components from a sketch or spec.
Data
Data Analysis
Exploring datasets, drawing conclusions, computing summary stats.
Data
JSON Extraction
Pulling structured fields out of unstructured text.
Data
Bulk Data Labeling
Cheaply tagging thousands of items with consistent labels.
Writing
Short-Form Summarization
TL;DRs of articles and emails at scale.
Similar models
google
Google: Gemma 4 26B A4B (free)
Free
262,144 ctx
100
google
Google: Gemma 4 26B A4B
$0.07 in / $0.35 out
262,144 ctx
100
google
Google: Gemma 4 31B
$0.13 in / $0.38 out
262,144 ctx
100
google
Google: Gemini 3.1 Flash Lite Preview
$0.25 in / $1.50 out
1,048,576 ctx
100
google
Google: Gemini 3.1 Pro Preview Custom Tools
$2.00 in / $12.00 out
1,048,576 ctx
100
google
Google: Gemini 3.1 Pro Preview
$2.00 in / $12.00 out
1,048,576 ctx
100