Gemma 4 31B (free)

GoogleFreeimage + text + video → textHugging Face OpenRouter

The cheapest provider for Gemma 4 31B (free) is DeepInfra at $0.153 per 1M tokens (blended), charging $0.09 per 1M input and $0.34 per 1M output tokens. 13 providers serve it; the most expensive charges 5.3× as much. Context window: 256K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.153

at DeepInfra

Input / output

$0.09 / $0.34

per 1M tokens

Providers

5.3× spread

7 days

—

best price

30 days

—

best price

Context

256K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for Google: Gemma 4 31B (free), USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
DeepInfraturboCheapest fp4	$0.09	$0.34	$0.153	best	256K	99.3%	Oct 3
DekaLLM	$0.10	$0.33	$0.158	+3%	256K	94.6%	Oct 3
CoreWeave fp4	$0.10	$0.34	$0.16	+5%	256K	99.6%	Oct 3
Venice fp4	$0.12	$0.36	$0.18	+18%	250K	99.4%	Oct 3
Chutes fp4	$0.12	$0.37	$0.183	+20%	128K	95.4%	Oct 3
Crusoe bf16	$0.14	$0.40	$0.205	+34%	256K	99.0%	Oct 3
Friendli	$0.14	$0.40	$0.205	+34%	256K	99.8%	Oct 3
Novita bf16	$0.14	$0.40	$0.205	+34%	256K	83.4%	Oct 3
DeepInfra fp8	$0.15	$0.40	$0.213	+39%	256K	98.0%	Oct 3
Parasail fp8	$0.15	$0.40	$0.213	+39%	256K	99.0%	Oct 3
Io Net	$0.38	$1.15	$0.573	+275%	256K	99.3%	Oct 3
SambaNova	$0.38	$1.15	$0.573	+275%	128K	97.5%	Oct 3
ModelRun fp4	$0.75	$1.00	$0.813	+433%	256K	99.8%	Oct 3
SiliconFlow fp8	$0.75	$1.00	$0.813	+433%	256K	81.1%	Oct 3

DeepInfraCheapest
turbo
$0.153
$0.09 in · $0.34 out
best
256K ctx99.3% uptimefp4
DekaLLM
$0.158
$0.10 in · $0.33 out
+3%
256K ctx94.6% uptime
CoreWeave
$0.16
$0.10 in · $0.34 out
+5%
256K ctx99.6% uptimefp4
Venice
$0.18
$0.12 in · $0.36 out
+18%
250K ctx99.4% uptimefp4
Chutes
$0.183
$0.12 in · $0.37 out
+20%
128K ctx95.4% uptimefp4
Crusoe
$0.205
$0.14 in · $0.40 out
+34%
256K ctx99.0% uptimebf16
Friendli
$0.205
$0.14 in · $0.40 out
+34%
256K ctx99.8% uptime
Novita
$0.205
$0.14 in · $0.40 out
+34%
256K ctx83.4% uptimebf16
DeepInfra
$0.213
$0.15 in · $0.40 out
+39%
256K ctx98.0% uptimefp8
Parasail
$0.213
$0.15 in · $0.40 out
+39%
256K ctx99.0% uptimefp8
Io Net
$0.573
$0.38 in · $1.15 out
+275%
256K ctx99.3% uptime
SambaNova
$0.573
$0.38 in · $1.15 out
+275%
128K ctx97.5% uptime
ModelRun
$0.813
$0.75 in · $1.00 out
+433%
256K ctx99.8% uptimefp4
SiliconFlow
$0.813
$0.75 in · $1.00 out
+433%
256K ctx81.1% uptimefp8

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
DeepInfra (turbo), DekaLLM	$0.05
CoreWeave	$0.10
Venice	$0.09
Chutes	$0.012
Crusoe	$0.14
Parasail	$0.06
Io Net	$0.19
ModelRun	$0.20
SiliconFlow	$0.25

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

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...

Released: Apr 2, 2026
First tracked: Oct 3, 2026
Canonical slug: google/gemma-4-31b-it-20260402
Weights: google/gemma-4-31B-it