Name: Gemma 4 31B IT
Brand: Google

Gemma 4 31B IT is Google's language model with a 262K context window and up to 131K output tokens, available from 6 providers, starting at $0.14 / 1M input and $0.4 / 1M output. Instruction-tuned 31B Gemma 4 model with multimodal capabilities including vision, tool use, and file input.

Specifications
Canonical ID	`google-gemma-4-31b-instruct`
Type	Language
Status	Active
Creator	Google
Providers	Hugging Face OpenRouter Libertai Tensormesh SambaNova Vercel AI Gateway
Context Window	262K tokens
Max Output	131K tokens
Input Modalities	ImagePDFTextVideo
Output Modalities	Text
Reasoning Efforts	default
Parameters	31B
HuggingFace Likes	2,208
HuggingFace Downloads (30d)	4,237,068
HuggingFace Downloads (all-time)	4,242,482
Release Date	2026-04-02 · 4 months ago

Capabilities

Input4/5

Text✓

Image✓

Audio·

Video✓

PDF✓

Output1/5

Text✓

Image·

Audio·

Video·

Embedding·

Capabilities5/13

Reasoning✓

Adaptive Reasoning·

Function Calling✓

Parallel Function Calling·

Structured Outputs✓

Native JSON Schema✓

Web Search·

URL Context·

Computer Use·

Code Execution·

File Search·

Prompt Caching✓

Assistant Prefill·

Pricing by Provider

US Dollar ($)

Per 1M tokens

Provider	Standard
Provider	Input $ / 1M	Output $ / 1M	Cache Read $ / 1M
Hugging Face `novita:google/gemma-4-31b-it`	$0.14	$0.4	N/A
Hugging Face `together_ai:google/gemma-4-31B-it`	$0.39	$0.97	N/A
Hugging Face `together_ai:pearl-ai/gemma-4-31b-it`	$0.28	$0.86	N/A
Libertai `libertai/gemma-4-31b-it`	$0.15	$0.4	N/A
OpenRouter `google/gemma-4-31b-it`	$0.22	$0.55	$0.12
SambaNova `sambanova/gemma-4-31B-it`	$0.38	$1.15	N/A
Tensormesh `tensormesh/google/gemma-4-31B-it`	$0.14	$0.56	N/A
Vercel AI Gateway `google/gemma-4-31b-it`	$0.14	$0.4	N/A

Cost Calculator

US Dollar ($)

Preset:

Input tokens

Output tokens

Cache write tokens

Cache read tokens

Number of calls

Cheapest Instances to Run It

Cloud GPU instances that can host Gemma 4 31B IT, ranked by cheapest on-demand price. The model needs about 74 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds

FP16 (full precision)

US Dollar ($)

Instance	Cloud	GPU	VRAM	Price	Cheapest region
Standard_NP20s	Azure	2× AMD Alveo U250 FPGA (64GB)	128 GB	$3.30/hr	westus2
g7e.2xlarge	AWS	RTX PRO Server 6000	96 GB	$3.36/hr	us-east-1
Standard_NC24ads_A100_v4	Azure	NVIDIA A100	80 GB	$3.67/hr	westus2
7 more instances can run Gemma 4 31B IT Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Versions

Version	Released	Context	Input / 1M	Output / 1M	Status
Gemma 4 26B A4B IT	2026-04-03	262K	$0.100	$0.300	Available
Gemma 4 31B IT	2026-04-02	262K	$0.140	$0.400	Current

Model IDs

accounts/fireworks/models/gemma-4-31b-it

accounts/fireworks/models/gemma-4-31b-it-nvfp4

google-gemma-4-31b-instruct

google/gemma-4-31b-it

google/gemma-4-31B-it

google/gemma-4-31b-it:free

huggingface-vlm-gemma-4-31b-it

libertai/gemma-4-31b-it

sambanova/gemma-4-31B-it

tensormesh/google/gemma-4-31B-it

Gemma 4 31B IT

CapabilitiesAPIGET/api/v1/models/google-gemma-4-31b-instruct

Pricing by ProviderAPIGET/api/v1/models/google-gemma-4-31b-instruct/pricing

Cost CalculatorAPIGET/api/v1/models/google-gemma-4-31b-instruct/pricing/calculate?input_tokens=1000000&output_tokens=500000

Cheapest Instances to Run ItAPIGET/api/v1/models/google-gemma-4-31b-instruct/instances

VersionsAPIGET/api/v1/models?family=gemma4

Model IDsAPIGET/api/v1/models/google-gemma-4-31b-instruct

Capabilities

Pricing by Provider

Cost Calculator

Cheapest Instances to Run It

Versions

Model IDs