GoogleVisionTool use

Gemma 4 31B pricing

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... Live index: 11 priced offers. Best input $0.0000 per million tokens from Google. Best output $0.0000 per million tokens from Google.

262K context·11 providers·verified Sep 20, 2026
Best inputFreeper 1M tokens · Google
Best outputFreeper 1M tokens · Google

Pricing across providers

All figures are list prices per million tokens unless a column says otherwise. 11 offers are listed for Gemma 4 31B. Best input in this view: Google.

A
Aihubmix
Input / 1M
$0.140
Output / 1M
$0.400
D
DeepInfra
Input / 1M
$0.090
Output / 1M
$0.340
Cached in: $0.050
F
Friendliai
Input / 1M
$0.140
Output / 1M
$0.400
L
Libertai
Input / 1M
$0.150
Output / 1M
$0.400
N
Novita
Input / 1M
$0.140
Output / 1M
$0.400
O
Openrouter
Input / 1M
$0.090
Output / 1M
$0.340
S
Sambanova
Input / 1M
$0.380
Output / 1M
$1.15
T
Tensormesh
Input / 1M
$0.140
Output / 1M
$0.560
Cached in: $0.0000
TA
Together AI
Input / 1M
$0.390
Output / 1M
$0.970
W
Wandb
Input / 1M
$0.100
Output / 1M
$0.340
G
Googlenative
Input / 1M
$0.0000
Output / 1M
$0.0000

Input vs output · per provider

Cost calculator

The calculator uses the same dollars per million tokens as the table. Adjust sliders to see how Gemma 4 31B cost scales with traffic.

Provider

In: $0.140/M·Out: $0.400/M

0.014000¢ / req

0.020000¢ / req

Daily
$3.40
Monthly
$102
Annual
$1.2K

Model specifications

Context length, caps, and capability flags for Gemma 4 31B. Values follow the main provider (Google) record in our index.

Context window
262,144 tokens
Max output
131,072 tokens
Vision (images)
Yes
Tool / function calling
Yes
Streaming
Yes
Released
Apr 2026
Primary provider
Google
Model family
N/A

Compare Gemma 4 31B

Open a pair page to see Gemma 4 31B next to another model with a shared provider matrix. 6 shortcuts below.

Locked

Compare with

Pick a model on both sides.

Popular Gemma 4 31B comparisons

Frequently asked questions

Quick frequently asked items for Gemma 4 31B pricing and limits. The short model note from our index: 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...

Gemma 4 31B costs $0.00 per million input tokens and $0.00 per million output tokens via the native API.

Related models

Models close to Gemma 4 31B by family, provider, and context window — each with live pricing in our catalog.