google

Google: Gemma 4 31B

Gemma 4 31B from Google is a versatile AI model capable of handling text, images, and video inputs, with a substantial context length of 262,144 tokens. It supports both reasoning and tool integration, making it suitable for complex tasks that require understanding across multiple modalities. This model excels in scenarios where you need a robust AI with broad capabilities, but at a higher cost due to its pay-per-token pricing of $0.12 for inputs and $0.37 for outputs. Its benchmark score of 57.2 across four independent tests indicates strong performance, though the coverage is moderate. Gemma 4 31B is ideal for projects requiring extensive input handling and diverse output capabilities within a budget that allows for higher costs.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.12
per 1M tokens
Output Price
$0.37
per 1M tokens
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 57.2 across 4 benchmarks, last refreshed 2026-07-21. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 48.4
AI Index Coding software engineering tasks 71.7
AI Index Agentic multi-step tool-using tasks 23.8
EQ-Bench emotional understanding in dialogue 70.8
Model ID
google/gemma-4-31b-it
Vendor
google
Released
April 2026
Tokenizer
Gemma
Input Modalities
image, text, video
Output Modalities
text
Max Output
16,384 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.12/M input and $0.37/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.08
A month of a busy support chatbot 5M in / 2M out $1.34

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-21 $0.12 $0.37 262,144
2026-07-17 $0.22 $0.55 262,144

Category rankings

Where Google: Gemma 4 31B places across the 25 categories it ranks in. How we rank →

#CategoryScore
#6 Real-Time ChatLatency · of 25 ranked 118
#7 Self-Hosted / LocalCost · of 25 ranked 117
#8 Social Media PostsWriting · of 25 ranked 119
#8 Voice Assistant BackendVoice · of 25 ranked 123
#8 Video SummarizationVideo · of 25 ranked 151
#8 Cheap Bulk InferenceCost · of 25 ranked 137
#11 Short-Form SummarizationWriting · of 25 ranked 129
#11 Chat CompanionPersonal · of 25 ranked 129
#12 Bulk Data LabelingData · of 25 ranked 133
#12 Email DraftingWriting · of 25 ranked 125
#12 Language LearningEducation · of 25 ranked 125
#12 Video Auto-TaggingVideo · of 25 ranked 123
#15 Image CaptioningVision · of 25 ranked 120
#15 Trivia & General KnowledgePersonal · of 25 ranked 119
#15 Dataset AnnotationResearch · of 25 ranked 141
#17 Code CompletionCode · of 25 ranked 132
#17 JSON ExtractionData · of 25 ranked 143
#19 Customer SupportBusiness · of 25 ranked 131
#19 Sales / Cold EmailBusiness · of 25 ranked 121
#19 Job Application DraftingBusiness · of 25 ranked 121
#19 Journaling HelperPersonal · of 25 ranked 121
#19 Recipe GenerationPersonal · of 25 ranked 121
#24 Resume WritingBusiness · of 25 ranked 115
#25 OCR / Document ParsingData · of 25 ranked 140
#25 Table Extraction from PDFsData · of 25 ranked 140

Similar models

Quick answers

How much does Google: Gemma 4 31B cost?
$0.12 per million input tokens and $0.37 per million output tokens.
What is Google: Gemma 4 31B's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does Google: Gemma 4 31B support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Google: Gemma 4 31B process images?
Yes, it accepts image input.