Gemma 4 31B IT

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 calling, and multilingual support across 140+ languages. Strong on coding, reasoning, and document understanding tasks. Apache 2.0 license.

google/gemma-4-31b-it

Organization: Google
Family: gemma
Providers: 45
Context: 262,144
Output limit: 32,768
Knowledge: 2025-01
Release: 2026-04-02
Updated: —
Weights: Open
Input: text, image/png, image/jpeg, image/webp, image/heic, image/heif
Output: text
Capabilities: —

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

65 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
Abacus	google/gemma-4-31b-it	262,144	131,072	— / —	—	—	—	View
ai&	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
AI/ML API	google/gemma-4-31b-it	256,000	16,384	— / —	—	—	—	View
Amazon Bedrock	google.gemma-4-31b	262,144	32,768	— / —	—	—	—	View
AMD	Gemma-4-31B-IT	262,144	32,768	— / —	—	—	—	View
Berget.AI	google/gemma-4-31B-it	128,000	8,192	— / —	—	—	—	View
Bothub	gemma-4-31b-it:free	262,144	32,768	— / —	—	—	—	View
Chutes	google/gemma-4-31B-turbo-TEE	131,072	65,536	— / —	—	—	—	View
CoreWeave	google/gemma-4-31B-it	262,144	262,144	— / —	—	—	—	View
Cortecs	gemma-4-31b-it	262,000	262,000	— / —	—	—	—	View
Crusoe	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
Deep Infra	google/gemma-4-31B-it	262,144	32,768	— / —	—	—	—	View
DevPass (LLM Gateway)	gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
DigitalOcean	gemma-4-31B-it	256,000	8,192	— / —	—	—	—	View
FastRouter	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
Friendli	google/gemma-4-31B-it	262,144	32,768	— / —	—	—	—	View
Hugging Face	google/gemma-4-31B-it	262,144	32,768	— / —	—	—	—	View
InferX	gemma-4-31B-it-fp8	262,144	32,768	— / —	—	—	—	View
Infomaniak	google/gemma-4-31B-it	100,000	32,768	— / —	—	—	—	View
Kenari	gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
Kilo Gateway	google/gemma-4-31b-it	262,144	16,384	— / —	—	—	—	View
Lilac	google/gemma-4-31b-it	262,100	262,100	— / —	—	—	—	View
LLM Gateway	deepinfra/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
LLM Gateway	consensusprotocol/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
LLM Gateway	novita/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
LLM Gateway	runware/gemma-4-31b-it	262,144	65,536	— / —	—	—	—	View
LLMTR	gemma-4	131,072	131,072	— / —	—	—	—	View
Merge Gateway	google/gemma-4-31b-it	262,144	65,536	— / —	—	—	—	View
Modular	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
NanoGPT	TEE/gemma4-31b	262,144	131,072	— / —	—	—	—	View
NanoGPT	google/gemma-4-31b-it:thinking	262,144	131,072	— / —	—	—	—	View
NanoGPT	TEE/gemma4-31b:thinking	262,144	131,072	— / —	—	—	—	View
NanoGPT	google/gemma-4-31b-it	262,144	131,072	— / —	—	—	—	View
NanoGPT	TEE/gemma-4-31b-it	262,144	262,144	— / —	—	—	—	View
Neuralwatt	gemma-4-31b	262,128	16,384	— / —	—	—	—	View
Novita AI	google/gemma-4-31b-it	262,144	131,072	— / —	—	—	—	View
Nvidia	google/gemma-4-31b-it	256,000	16,384	— / —	—	—	—	View
Ollama Cloud	gemma4:31b	262,144	262,144	— / —	—	—	—	View
Chutesvia OpenRouter	google/gemma-4-31b-it fp4	131,072	65,536	$0.12 / $0.37	Yes	Yes	Yes	View
CoreWeavevia OpenRouter	google/gemma-4-31b-it fp4	262,144	235,929	$0.10 / $0.34	Yes	Yes	Yes	View
Crusoevia OpenRouter	google/gemma-4-31b-it bf16	262,144	262,141	$0.14 / $0.40	Yes	Yes	Yes	View
DeepInfravia OpenRouter	google/gemma-4-31b-it fp4	262,144	16,384	$0.09 / $0.34	Yes	Yes	Yes	View
DeepInfravia OpenRouter	google/gemma-4-31b-it fp8	262,144	16,384	$0.20 / $0.40	Yes	Yes	Yes	View
Friendlivia OpenRouter	google/gemma-4-31b-it unknown	262,144	8,192	$0.14 / $0.40	Yes	Yes	Yes	View
Google AI Studiovia OpenRouter	google/gemma-4-31b-it:free unknown	262,144	32,768	$0.00 / $0.00	Yes	Yes	No	View
Io Netvia OpenRouter	google/gemma-4-31b-it unknown	262,144	16,384	$0.361 / $1.0925	Yes	Yes	No	View
ModelRunvia OpenRouter	google/gemma-4-31b-it fp4	262,144	235,929	$0.75 / $1.00	Yes	Yes	Yes	View
Novitavia OpenRouter	google/gemma-4-31b-it bf16	262,144	131,072	$0.14 / $0.40	Yes	Yes	Yes	View
Parasailvia OpenRouter	google/gemma-4-31b-it fp8	262,144	235,929	$0.15 / $0.40	Yes	Yes	Yes	View
SambaNovavia OpenRouter	google/gemma-4-31b-it unknown	131,072	117,964	$0.38 / $1.15	Yes	Yes	No	View
SiliconFlowvia OpenRouter	google/gemma-4-31b-it fp8	262,144	235,929	$0.75 / $1.00	Yes	Yes	Yes	View
Venicevia OpenRouter	google/gemma-4-31b-it fp4	256,000	8,192	$0.12 / $0.36	Yes	Yes	Yes	View
Opper	gemma-4-31b-it	256,000	8,192	— / —	—	—	—	View
OrcaRouter	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
Poe	google/gemma-4-31b	262,144	8,192	— / —	—	—	—	View
QVAC	gemma4-31b	262,144	32,768	— / —	—	—	—	View
Regolo AI	gemma4-31b	100,000	100,000	— / —	—	—	—	View
Requesty	gemma-4-31b-it	262,144	8,192	— / —	—	—	—	View
SambaNova	gemma-4-31B-it	131,072	131,072	— / —	—	—	—	View
SiliconFlow	google/gemma-4-31B-it	262,144	262,144	— / —	—	—	—	View
Tempr Gateway	google/gemma-4-31b-it	262,144	32,768	— / —	—	—	—	View
Tinfoil	gemma4-31b	262,144	32,768	— / —	—	—	—	View
UnoRouter	gemma-4-31b-it:free	262,144	32,768	— / —	—	—	—	View
Venice AI	google-gemma-4-31b-it	256,000	16,384	— / —	—	—	—	View
Vercel AI Gateway	google/gemma-4-31b-it	262,144	131,072	— / —	—	—	—	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers65Across 45 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 10 lowest-priced configurations

InputOutput

Google AI Studiogoogle-ai-studio

$0.00$0.00

DeepInfradeepinfra/turbo

$0.09$0.34

CoreWeavecoreweave/fp4

$0.10$0.34

Chuteschutes/fp4

$0.12$0.37

Venicevenice/fp4

$0.12$0.36

Crusoecrusoe/bf16

$0.14$0.40

Friendlifriendli

$0.14$0.40

Novitanovita/bf16

$0.14$0.40

Parasailparasail/fp8

$0.15$0.40

DeepInfradeepinfra/fp8

$0.20$0.40

google/gemma-4-31b-itObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.09
Output: $0.34
Cache read: $0.05

google/gemma-4-31b-it:freeObserved Oct 10, 2026, 11:31 AM UTC

Input: $0.00
Output: $0.00

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Chuteschutes/fp4	$0.12	$0.37	$0.012	—
CoreWeavecoreweave/fp4	$0.10	$0.34	$0.10	—
Crusoecrusoe/bf16	$0.14	$0.40	$0.14	—
DeepInfradeepinfra/turbo	$0.09	$0.34	$0.05	—
DeepInfradeepinfra/fp8	$0.20	$0.40	—	—
Friendlifriendli	$0.14	$0.40	—	—
Io Netio-net	$0.361	$1.0925	$0.1805	—
ModelRunmodelrun/fp4	$0.75	$1.00	$0.20	—
Novitanovita/bf16	$0.14	$0.40	—	—
Parasailparasail/fp8	$0.15	$0.40	$0.06	—
SambaNovasambanova	$0.38	$1.15	—	—
SiliconFlowsiliconflow/fp8	$0.75	$1.00	$0.25	—
Venicevenice/fp4	$0.12	$0.36	$0.09	—
Google AI Studiogoogle-ai-studio	$0.00	$0.00	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Chuteschutes/fp4

5,595.5–26,422.76 ms

CoreWeavecoreweave/fp4

483–4,119.42 ms

Crusoecrusoe/bf16

609–3,209.31 ms

DeepInfradeepinfra/turbo

557–6,114.76 ms

DeepInfradeepinfra/fp8

2,113.5–54,169.33 ms

Friendlifriendli

488–4,133 ms

All latency percentiles 14 endpoints

Endpoint	P50	P75	P90	P99
Chuteschutes/fp4	5,595.5 ms	11,348 ms	15,289.4 ms	26,422.76 ms
CoreWeavecoreweave/fp4	483 ms	738 ms	1,106.9 ms	4,119.42 ms
Crusoecrusoe/bf16	609 ms	828 ms	1,202.5 ms	3,209.31 ms
DeepInfradeepinfra/turbo	557 ms	1,050.25 ms	1,757 ms	6,114.76 ms
DeepInfradeepinfra/fp8	2,113.5 ms	10,384.75 ms	27,270.1 ms	54,169.33 ms
Friendlifriendli	488 ms	1,311.25 ms	2,095.8 ms	4,133 ms
Io Netio-net	612 ms	1,357.5 ms	2,304.4 ms	14,133.66 ms
ModelRunmodelrun/fp4	154 ms	265.25 ms	457 ms	1,375.18 ms
Novitanovita/bf16	849 ms	1,274 ms	2,591 ms	21,244 ms
Parasailparasail/fp8	3,335 ms	8,892.25 ms	20,163.1 ms	55,897.74 ms
SambaNovasambanova	1,534.5 ms	2,383.5 ms	4,043.8 ms	6,993.84 ms
SiliconFlowsiliconflow/fp8	1,306.5 ms	2,627.5 ms	7,206.5 ms	28,803.5 ms
Venicevenice/fp4	461 ms	668 ms	1,021.9 ms	2,853 ms
Google AI Studiogoogle-ai-studio	1,175 ms	1,771.5 ms	5,225.2 ms	39,984.06 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 6 endpoints

P50P75P90P99

Chuteschutes/fp4

10–33 t/s

CoreWeavecoreweave/fp4

30–107 t/s

Crusoecrusoe/bf16

27–93 t/s

DeepInfradeepinfra/turbo

38–67 t/s

DeepInfradeepinfra/fp8

27–40 t/s

Friendlifriendli

133–273 t/s

All throughput percentiles 14 endpoints

Endpoint	P50	P75	P90	P99
Chuteschutes/fp4	10 t/s	12 t/s	15 t/s	33 t/s
CoreWeavecoreweave/fp4	30 t/s	42 t/s	60 t/s	107 t/s
Crusoecrusoe/bf16	27 t/s	39 t/s	56 t/s	93 t/s
DeepInfradeepinfra/turbo	38 t/s	47 t/s	54 t/s	67 t/s
DeepInfradeepinfra/fp8	27 t/s	30 t/s	33 t/s	40 t/s
Friendlifriendli	133 t/s	164 t/s	202 t/s	273 t/s
Io Netio-net	33 t/s	38 t/s	41 t/s	46 t/s
ModelRunmodelrun/fp4	220 t/s	294 t/s	340 t/s	396 t/s
Novitanovita/bf16	25 t/s	28 t/s	30 t/s	34 t/s
Parasailparasail/fp8	18 t/s	22 t/s	28 t/s	40 t/s
SambaNovasambanova	102.5 t/s	135.5 t/s	187.3 t/s	201.98 t/s
SiliconFlowsiliconflow/fp8	45 t/s	52 t/s	60.2 t/s	67 t/s
Venicevenice/fp4	36 t/s	45 t/s	52 t/s	64.86 t/s
Google AI Studiogoogle-ai-studio	31 t/s	33 t/s	35 t/s	36 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 14 endpoints

Endpoint5 minutes30 minutes24 hours

Chuteschutes/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

83.33%

82.33%

CoreWeavecoreweave/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

Crusoecrusoe/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

98.64%

DeepInfradeepinfra/turboObserved Oct 10, 2026, 11:31 AM UTC

100%

DeepInfradeepinfra/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

FriendlifriendliObserved Oct 10, 2026, 11:31 AM UTC

100%

Io Netio-netObserved Oct 10, 2026, 11:31 AM UTC

100%

98.81%

ModelRunmodelrun/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

99.93%

Novitanovita/bf16Observed Oct 10, 2026, 11:31 AM UTC

100%

63.82%

Parasailparasail/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

99.79%

SambaNovasambanovaObserved Oct 10, 2026, 11:31 AM UTC

100%

84.4%

SiliconFlowsiliconflow/fp8Observed Oct 10, 2026, 11:31 AM UTC

100%

97.47%

Venicevenice/fp4Observed Oct 10, 2026, 11:31 AM UTC

100%

94.42%

Google AI Studiogoogle-ai-studioObserved Oct 10, 2026, 11:31 AM UTC

100%

99.62%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

google/gemma-4-31b-itObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 50

Coding

43.4

Agentic

4.2

Intelligence

14.7

google/gemma-4-31b-it:freeObserved Oct 10, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 50

Coding

43.4

Agentic

4.2

Intelligence

14.7

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

gpqa diamondGoogle: Gemma 4 31B

82.251%

tau bench verified airlineGoogle: Gemma 4 31B

75.619%

Evaluation	Configuration	Source	Results	Details
gpqa diamond	Google: Gemma 4 31Bgoogle/gemma-4-31b-it-20260402	OpenRouter	82.251%	Details
tau bench verified airline	Google: Gemma 4 31Bgoogle/gemma-4-31b-it-20260402	OpenRouter	75.619%	Details
Composite indices	Gemma 4 31B (Reasoning)google/gemma-4-31b-it-20260402	Artificial Analysis	Intelligence 4.4 · Coding 43.4 · Agentic 4.2	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Nov 14, 2026.

Apps & session costs

Compare observed median session costs for applications using this model, grouped by conversation length.

30-day sample · through Nov 1, 2026

Application	Model route	Turns	Median cost / session	Details
Hermes Agent	google/gemma-4-31b-it-20260402	10–49 turns	$0.063721	Details
Hermes Agent	google/gemma-4-31b-it-20260402	1 turn	$0.000744	Details
Hermes Agent	google/gemma-4-31b-it-20260402	2–9 turns	$0.004554	Details

Source: OpenRouter, as of Nov 9, 2026. Published under CC BY 4.0. These are observed costs per session, not token prices or a forecast for your workload. Apps are compared separately.

Activity

Daily prompt and completion tokens reported for this model's routes in OpenRouter's top 50. Missing days have no published value.

Last 90 complete UTC days

Daily token usage5,381,973,724,774 reported tokens · 88 days with observations

92B0

2026-08-16
45,677,203,868 tokens

2026-08-17
51,195,386,224 tokens

2026-08-18
54,075,051,335 tokens

2026-08-19
58,139,714,223 tokens

2026-08-20
84,264,076,321 tokens

2026-08-21
54,266,275,128 tokens

2026-08-22
42,028,494,016 tokens

2026-08-23
43,115,910,914 tokens

2026-08-24
49,790,990,936 tokens

2026-08-25
50,338,770,724 tokens

2026-08-26
49,059,527,236 tokens

2026-08-27
52,032,833,915 tokens

2026-08-28
47,157,490,810 tokens

2026-08-29
38,983,336,477 tokens

2026-08-30
41,563,662,968 tokens

2026-08-31
45,667,405,091 tokens

2026-09-01
50,027,952,246 tokens

2026-09-02
58,893,691,236 tokens

2026-09-03
56,986,582,413 tokens

2026-09-04
48,998,207,263 tokens

2026-09-05
42,123,096,197 tokens

2026-09-06
45,994,206,414 tokens

2026-09-07
47,785,651,472 tokens

2026-09-08
59,357,498,195 tokens

2026-09-09
55,589,992,139 tokens

2026-09-10
58,128,636,416 tokens

2026-09-11
51,996,290,589 tokens

2026-09-12
43,656,873,861 tokens

2026-09-13
43,196,690,192 tokens

2026-09-14
54,386,645,675 tokens

2026-09-15
71,488,436,838 tokens

2026-09-16
55,457,705,000 tokens

2026-09-17
57,260,692,865 tokens

2026-09-18
54,634,084,132 tokens

2026-09-19
44,196,526,918 tokens

2026-09-20
50,602,610,919 tokens

2026-09-21
60,695,896,767 tokens

2026-09-22
62,833,338,256 tokens

2026-09-23
58,400,449,700 tokens

2026-09-24
57,208,674,107 tokens

2026-09-25
60,412,029,609 tokens

2026-09-26
58,028,444,980 tokens

2026-09-27
60,886,166,075 tokens

2026-09-28
67,326,788,634 tokens

2026-09-29
70,119,450,276 tokens

2026-09-30
68,051,662,773 tokens

2026-10-01
71,271,670,453 tokens

2026-10-02
63,662,661,568 tokens

2026-10-03
58,887,262,957 tokens

2026-10-04
54,465,824,777 tokens

2026-10-05
63,093,048,230 tokens

2026-10-06
61,769,768,049 tokens

2026-10-07
67,744,228,368 tokens

2026-10-08
68,012,026,124 tokens

2026-10-09
70,381,255,634 tokens

2026-10-10
65,182,211,972 tokens

2026-10-11
64,435,690,472 tokens

2026-10-12
72,978,554,465 tokens

2026-10-13
72,849,266,420 tokens

2026-10-14
74,102,724,389 tokens

2026-10-15
77,250,459,596 tokens

2026-10-16
73,136,257,496 tokens

2026-10-17
89,214,129,380 tokens

2026-10-18
70,853,806,816 tokens

2026-10-19
74,717,860,745 tokens

2026-10-20
92,043,975,408 tokens

2026-10-21
84,658,760,411 tokens

2026-10-22
78,397,761,988 tokens

2026-10-23
63,611,895,825 tokens

2026-10-24
52,058,806,755 tokens

2026-10-25
53,177,117,616 tokens

2026-10-26
66,412,986,425 tokens

2026-10-27
62,749,947,204 tokens

2026-10-28
73,309,614,297 tokens

2026-10-29
78,249,046,182 tokens

2026-10-30
77,554,470,458 tokens

2026-10-31
67,450,727,526 tokens

2026-11-01
68,372,891,963 tokens

2026-11-02
68,458,668,361 tokens

2026-11-03
71,458,516,992 tokens

2026-11-04
68,088,413,225 tokens

2026-11-05
65,984,981,852 tokens

2026-11-06
68,395,959,390 tokens

2026-11-07
54,723,508,693 tokens

2026-11-08
58,137,639,944 tokens

2026-11-09
65,404,935,131 tokens

2026-11-10
69,544,819,823 tokens

2026-11-13
77,638,469,051 tokens

Aug 16, 2026Nov 13, 2026

Daily observations · 88 days

Date (UTC)	Reported tokens	Reported routes
Nov 13, 2026	77,638,469,051	1
Nov 10, 2026	69,544,819,823	1
Nov 9, 2026	65,404,935,131	1
Nov 8, 2026	58,137,639,944	1
Nov 7, 2026	54,723,508,693	1
Nov 6, 2026	68,395,959,390	1
Nov 5, 2026	65,984,981,852	1
Nov 4, 2026	68,088,413,225	1
Nov 3, 2026	71,458,516,992	1
Nov 2, 2026	68,458,668,361	1
Nov 1, 2026	68,372,891,963	1
Oct 31, 2026	67,450,727,526	1
Oct 30, 2026	77,554,470,458	1
Oct 29, 2026	78,249,046,182	1
Oct 28, 2026	73,309,614,297	1
Oct 27, 2026	62,749,947,204	1
Oct 26, 2026	66,412,986,425	1
Oct 25, 2026	53,177,117,616	1
Oct 24, 2026	52,058,806,755	1
Oct 23, 2026	63,611,895,825	1
Oct 22, 2026	78,397,761,988	1
Oct 21, 2026	84,658,760,411	1
Oct 20, 2026	92,043,975,408	1
Oct 19, 2026	74,717,860,745	1
Oct 18, 2026	70,853,806,816	1
Oct 17, 2026	89,214,129,380	1
Oct 16, 2026	73,136,257,496	1
Oct 15, 2026	77,250,459,596	1
Oct 14, 2026	74,102,724,389	1
Oct 13, 2026	72,849,266,420	1
Oct 12, 2026	72,978,554,465	1
Oct 11, 2026	64,435,690,472	1
Oct 10, 2026	65,182,211,972	1
Oct 9, 2026	70,381,255,634	1
Oct 8, 2026	68,012,026,124	1
Oct 7, 2026	67,744,228,368	1
Oct 6, 2026	61,769,768,049	1
Oct 5, 2026	63,093,048,230	1
Oct 4, 2026	54,465,824,777	1
Oct 3, 2026	58,887,262,957	1
Oct 2, 2026	63,662,661,568	1
Oct 1, 2026	71,271,670,453	1
Sep 30, 2026	68,051,662,773	1
Sep 29, 2026	70,119,450,276	1
Sep 28, 2026	67,326,788,634	1
Sep 27, 2026	60,886,166,075	1
Sep 26, 2026	58,028,444,980	1
Sep 25, 2026	60,412,029,609	1
Sep 24, 2026	57,208,674,107	1
Sep 23, 2026	58,400,449,700	1
Sep 22, 2026	62,833,338,256	1
Sep 21, 2026	60,695,896,767	1
Sep 20, 2026	50,602,610,919	1
Sep 19, 2026	44,196,526,918	1
Sep 18, 2026	54,634,084,132	1
Sep 17, 2026	57,260,692,865	1
Sep 16, 2026	55,457,705,000	1
Sep 15, 2026	71,488,436,838	1
Sep 14, 2026	54,386,645,675	1
Sep 13, 2026	43,196,690,192	1
Sep 12, 2026	43,656,873,861	1
Sep 11, 2026	51,996,290,589	1
Sep 10, 2026	58,128,636,416	1
Sep 9, 2026	55,589,992,139	1
Sep 8, 2026	59,357,498,195	1
Sep 7, 2026	47,785,651,472	1
Sep 6, 2026	45,994,206,414	1
Sep 5, 2026	42,123,096,197	1
Sep 4, 2026	48,998,207,263	1
Sep 3, 2026	56,986,582,413	1
Sep 2, 2026	58,893,691,236	1
Sep 1, 2026	50,027,952,246	1
Aug 31, 2026	45,667,405,091	1
Aug 30, 2026	41,563,662,968	1
Aug 29, 2026	38,983,336,477	1
Aug 28, 2026	47,157,490,810	1
Aug 27, 2026	52,032,833,915	1
Aug 26, 2026	49,059,527,236	1
Aug 25, 2026	50,338,770,724	1
Aug 24, 2026	49,790,990,936	1
Aug 23, 2026	43,115,910,914	1
Aug 22, 2026	42,028,494,016	1
Aug 21, 2026	54,266,275,128	1
Aug 20, 2026	84,264,076,321	1
Aug 19, 2026	58,139,714,223	1
Aug 18, 2026	54,075,051,335	1
Aug 17, 2026	51,195,386,224	1
Aug 16, 2026	45,677,203,868	1

Source: OpenRouter (openrouter.ai/rankings), as of Nov 14, 2026. CC BY 4.0. Totals include only individually published routes. Tokenizers differ by provider; the aggregated “other” category is never assigned to a model.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

google/gemma-4-31b-itObserved Oct 10, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 16,384
Tokenizer: Gemma
Input: image, text, video
Output: text
Moderation: No
Added to OpenRouter: 2026-04-02

Base URLhttps://openrouter.ai/api/v1

Model IDgoogle/gemma-4-31b-it

Version IDgoogle/gemma-4-31b-it-20260402

Weights IDgoogle/gemma-4-31B-it

Reasoning

Required: No
Enabled by default: No
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Default parameters

top k: 64
top p: 0.95
temperature: 1

google/gemma-4-31b-it:freeObserved Oct 10, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 32,768
Tokenizer: Gemma
Input: image, text, video
Output: text
Moderation: No
Added to OpenRouter: 2026-04-02

Base URLhttps://openrouter.ai/api/v1

Model IDgoogle/gemma-4-31b-it:free

Version IDgoogle/gemma-4-31b-it-20260402

Weights IDgoogle/gemma-4-31B-it

Reasoning

Required: No
Enabled by default: No
Default effort: —
Supported efforts: —

Supported parameters

include_reasoning
max_tokens
reasoning
response_format
seed
temperature
tool_choice
tools
top_p

Default parameters

top k: 64
top p: 0.95
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Gemma 4 31B IT cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Gemma 4 31B IT?

There are 65 cataloged offers across 45 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Not reported. Structured output: Not reported. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 4 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 21, 2026 · bbaaf2ad72a7
Oct 20, 2026 · 46bd8c7f3256
Sep 14, 2026 · fa9973480682
Sep 12, 2026 · 543f0b05f2db