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.
- Organization
- Family
- gemma
- Providers
- 37
- Context
- 262,144
- Output limit
- 32,768
- Knowledge
- —
- Release
- 2026-04-02
- Updated
- 2026-04-02
- Weights
- Open
- Input
- text, image
- Output
- text
- Capabilities
- Tools, Reasoning, Structured, Temperature
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Abacus | google/gemma-4-31b-it | 262,144 | 131,072 | $0.14 / $0.40 | Yes | Yes | Yes | View |
| ai& | google/gemma-4-31b-it | 262,144 | 32,768 | $0.20 / $0.50 | Yes | Yes | Yes | View |
| Amazon Bedrock | google.gemma-4-31b | 262,144 | 32,768 | $0.14 / $0.40 | Yes | Yes | Yes | View |
| Bothub | gemma-4-31b-it:free | 262,144 | 32,768 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Chutes | google/gemma-4-31B-turbo-TEE | 131,072 | 65,536 | $0.12 / $0.37 | Yes | Yes | Yes | View |
| CoreWeave | google/gemma-4-31B-it | 262,144 | 262,144 | $0.10 / $0.34 | Yes | Yes | Yes | View |
| Cortecs | gemma-4-31b-it | 262,000 | 262,000 | $0.223 / $0.39 | Yes | Yes | Yes | View |
| CrofAI | gemma-4-31b-it | 262,144 | 262,144 | $0.10 / $0.30 | Yes | Yes | Yes | View |
| Crusoe | google/gemma-4-31b-it | 262,144 | 32,768 | $0.14 / $0.40 | Yes | Yes | Yes | View |
| Deep Infra | google/gemma-4-31B-it | 262,144 | 32,768 | $0.15 / $0.40 | Yes | Yes | Yes | View |
| DevPass (LLM Gateway) | gemma-4-31b-it | 262,144 | 32,768 | $0.10 / $0.25 | Yes | Yes | Yes | View |
| FastRouter | google/gemma-4-31b-it | 262,144 | 32,768 | $0.13 / $0.38 | Yes | Yes | Yes | View |
| Friendli | google/gemma-4-31B-it | 262,144 | 32,768 | $0.14 / $0.40 | Yes | Yes | Yes | View |
| Hugging Face | google/gemma-4-31B-it | 262,144 | 32,768 | $0.14 / $0.40 | Yes | Yes | Yes | View |
| InferX | gemma-4-31B-it-fp8 | 262,144 | 32,768 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Infomaniak | google/gemma-4-31B-it | 100,000 | 32,768 | $0.25 / $0.50 | Yes | Yes | Yes | View |
| Kenari | gemma-4-31b-it | 262,144 | 32,768 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Kilo Gateway | google/gemma-4-31b-it | 262,144 | 16,384 | $0.09 / $0.34 | Yes | Yes | Yes | View |
| Lilac | google/gemma-4-31b-it | 262,100 | 262,100 | $0.11 / $0.35 | Yes | Yes | Yes | View |
| LLM Gateway | scx-ai/gemma-4-31b-it | 131,072 | 8,192 | $0.30 / $0.91 | No | Yes | No | View |
| LLM Gateway | deepinfra/gemma-4-31b-it | 262,144 | 32,768 | $0.15 / $0.40 | Yes | Yes | No | View |
| LLM Gateway | consensusprotocol/gemma-4-31b-it | 262,144 | 32,768 | $0.10 / $0.25 | Yes | Yes | No | View |
| LLM Gateway | novita/gemma-4-31b-it | 262,144 | 32,768 | $0.14 / $0.40 | No | Yes | No | View |
| LLM Gateway | runware/gemma-4-31b-it | 262,144 | 65,536 | $0.102 / $0.297 | Yes | Yes | No | View |
| LLM Gateway | cerebras/gemma-4-31b-it | 131,072 | 32,768 | $0.99 / $1.49 | Yes | Yes | No | View |
| LLMTR | gemma-4 | 131,072 | 131,072 | $2.00 / $5.00 | Yes | Yes | Yes | View |
| Merge Gateway | google/gemma-4-31b-it | 262,144 | 65,536 | $0.14 / $0.40 | Yes | No | No | View |
| NanoGPT | google/gemma-4-31b-it:thinking | 262,144 | 131,072 | $0.10 / $0.35 | Yes | Yes | Yes | View |
| NanoGPT | google/gemma-4-31b-it | 262,144 | 131,072 | $0.10 / $0.45 | Yes | Yes | Yes | View |
| NanoGPT | TEE/gemma-4-31b-it | 262,144 | 262,144 | $0.15 / $0.46 | Yes | Yes | No | View |
| Neuralwatt | gemma-4-31b | 262,128 | 16,384 | $0.144 / $0.42 | Yes | Yes | Yes | 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 | No | Yes | View |
| DeepInfravia OpenRouter | google/gemma-4-31b-it fp8 | 262,144 | 16,384 | $0.15 / $0.40 | Yes | Yes | Yes | View |
| DekaLLMvia OpenRouter | google/gemma-4-31b-it unknown | 262,144 | 235,929 | $0.10 / $0.33 | 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 | $0.38 / $1.15 | 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 | $0.46488 / $2.44062 | Yes | Yes | Yes | View |
| OrcaRouter | google/gemma-4-31b-it | 262,144 | 32,768 | $0.13 / $0.38 | Yes | Yes | Yes | View |
| Pioneer | google/gemma-4-31B-it | 32,768 | 32,768 | $0.50 / $0.50 | Yes | Yes | Yes | View |
| QVAC | gemma4-31b | 262,144 | 32,768 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Regolo AI | gemma4-31b | 100,000 | 100,000 | $0.46 / $2.42 | Yes | Yes | Yes | View |
| Requesty | gemma-4-31b-it | 262,144 | 8,192 | $0.00 / $0.00 | Yes | Yes | No | View |
| SiliconFlow | google/gemma-4-31B-it | 262,144 | 262,144 | $0.13 / $0.40 | No | Yes | Yes | View |
| Tempr Gateway | google/gemma-4-31b-it | 262,144 | 32,768 | — / — | Yes | Yes | Yes | View |
| Tinfoil | gemma4-31b | 262,144 | 32,768 | $0.40 / $1.00 | Yes | Yes | Yes | View |
| UnoRouter | gemma-4-31b-it:free | 262,144 | 32,768 | $0.00 / $0.00 | Yes | Yes | Yes | View |
| Venice AI | google-gemma-4-31b-it | 256,000 | 8,192 | $0.12 / $0.36 | Yes | Yes | Yes | View |
| Vercel AI Gateway | google/gemma-4-31b-it | 262,144 | 131,072 | $0.14 / $0.40 | No | Yes | Yes | 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.
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.
google/gemma-4-31b-itObserved - Input
- $0.09
- Output
- $0.34
- Cache read
- $0.05
google/gemma-4-31b-it:freeObserved - 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 | $0.15 | $0.40 | — | — |
| DekaLLMdekallm | $0.10 | $0.33 | $0.05 | — |
| Friendlifriendli | $0.14 | $0.40 | — | — |
| Io Netio-net | $0.38 | $1.15 | $0.19 | — |
| 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.
Time to first token · milliseconds
All latency percentiles 15 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Chuteschutes/fp4 | 2,558 ms | 4,912.5 ms | 8,547.6 ms | 22,870.27 ms |
| CoreWeavecoreweave/fp4 | 391 ms | 642.25 ms | 1,266.9 ms | 4,878.62 ms |
| Crusoecrusoe/bf16 | 487 ms | 712 ms | 1,201.8 ms | 8,009 ms |
| DeepInfradeepinfra/turbo | 574.5 ms | 1,024 ms | 1,744 ms | 5,321.94 ms |
| DeepInfradeepinfra/fp8 | 1,762 ms | 3,125.25 ms | 5,426 ms | 11,978.26 ms |
| DekaLLMdekallm | 1,107 ms | 2,156 ms | 4,018.4 ms | 10,305.72 ms |
| Friendlifriendli | 246 ms | 809 ms | 1,670.9 ms | 4,043.81 ms |
| Io Netio-net | 501 ms | 1,491.5 ms | 3,283.2 ms | 6,886.86 ms |
| ModelRunmodelrun/fp4 | 189 ms | 268 ms | 362 ms | 1,012.09 ms |
| Novitanovita/bf16 | 1,266 ms | 13,044.5 ms | 32,622.4 ms | 73,495.85 ms |
| Parasailparasail/fp8 | 1,320 ms | 2,242.25 ms | 3,679.8 ms | 9,264.13 ms |
| SambaNovasambanova | 3,033 ms | 7,578.75 ms | 9,804 ms | 35,853.55 ms |
| SiliconFlowsiliconflow/fp8 | 1,237 ms | 1,627.5 ms | 3,455.2 ms | 5,537.78 ms |
| Venicevenice/fp4 | 482 ms | 751 ms | 1,161 ms | 2,963.63 ms |
| Google AI Studiogoogle-ai-studio | 1,215 ms | 1,715 ms | 4,051.6 ms | 38,563.67 ms |
Output throughput · tokens per second
All throughput percentiles 15 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Chuteschutes/fp4 | 22 t/s | 35 t/s | 50 t/s | 85 t/s |
| CoreWeavecoreweave/fp4 | 43 t/s | 59 t/s | 79 t/s | 113 t/s |
| Crusoecrusoe/bf16 | 34 t/s | 51 t/s | 73 t/s | 105.73 t/s |
| DeepInfradeepinfra/turbo | 42 t/s | 51 t/s | 58 t/s | 71 t/s |
| DeepInfradeepinfra/fp8 | 18 t/s | 21 t/s | 25 t/s | 33 t/s |
| DekaLLMdekallm | 24 t/s | 36 t/s | 54 t/s | 95 t/s |
| Friendlifriendli | 118 t/s | 157 t/s | 208 t/s | 295 t/s |
| Io Netio-net | 38 t/s | 44 t/s | 45 t/s | 46.74 t/s |
| ModelRunmodelrun/fp4 | 230 t/s | 261 t/s | 324 t/s | 384 t/s |
| Novitanovita/bf16 | 28 t/s | 33 t/s | 36 t/s | 39 t/s |
| Parasailparasail/fp8 | 23 t/s | 29 t/s | 36 t/s | 50 t/s |
| SambaNovasambanova | 79 t/s | 114 t/s | 143.5 t/s | 165.85 t/s |
| SiliconFlowsiliconflow/fp8 | 41 t/s | 48 t/s | 58 t/s | 64.45 t/s |
| Venicevenice/fp4 | 43 t/s | 52 t/s | 59 t/s | 68 t/s |
| Google AI Studiogoogle-ai-studio | 29 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.
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.
google/gemma-4-31b-itObserved google/gemma-4-31b-it:freeObserved Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| Composite indices | Gemma 4 31B (Reasoning)google/gemma-4-31b-it-20260402 | Artificial Analysis | Intelligence 14.7 · Coding 43.4 · Agentic 4.2 | Details |
| gpqa diamond | Google: Gemma 4 31Bgoogle/gemma-4-31b-it-20260402 | OpenRouter | 81.794% | Details |
| tau bench verified airline | Google: Gemma 4 31Bgoogle/gemma-4-31b-it-20260402 | OpenRouter | 76.682% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Apps & session costs
Compare observed median session costs for applications using this model, grouped by conversation length.
| Application | Model route | Turns | Median cost / session | Details |
|---|---|---|---|---|
| Hermes Agent | google/gemma-4-31b-it-20260402 | 2–9 turns | $0.007523 | Details |
| Hermes Agent | google/gemma-4-31b-it-20260402 | 1 turn | $0.001703 | Details |
| Hermes Agent | google/gemma-4-31b-it-20260402 | 10–49 turns | $0.092514 | Details |
Source: OpenRouter, as of Oct 2, 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.
46,755,301,879 tokens
45,658,252,754 tokens
44,530,904,215 tokens
50,126,368,594 tokens
40,620,552,025 tokens
40,527,579,540 tokens
48,915,978,436 tokens
45,717,012,237 tokens
46,111,510,701 tokens
48,291,474,713 tokens
50,878,261,392 tokens
47,768,892,422 tokens
45,525,733,011 tokens
50,749,767,126 tokens
55,210,350,997 tokens
59,735,936,886 tokens
56,373,530,367 tokens
54,956,549,011 tokens
46,328,267,209 tokens
47,150,857,085 tokens
54,833,836,735 tokens
57,046,179,599 tokens
55,898,837,571 tokens
60,257,543,548 tokens
67,704,518,305 tokens
59,832,944,881 tokens
58,206,755,880 tokens
58,380,676,115 tokens
55,964,966,146 tokens
58,317,628,475 tokens
59,946,744,190 tokens
62,261,223,176 tokens
56,666,442,277 tokens
62,601,543,555 tokens
60,349,064,056 tokens
86,793,779,422 tokens
90,514,544,009 tokens
88,309,998,870 tokens
54,554,005,596 tokens
49,407,478,743 tokens
45,677,203,868 tokens
51,195,386,224 tokens
54,075,051,335 tokens
58,139,714,223 tokens
84,264,076,321 tokens
54,266,275,128 tokens
42,028,494,016 tokens
43,115,910,914 tokens
49,790,990,936 tokens
50,338,770,724 tokens
49,059,527,236 tokens
52,032,833,915 tokens
47,157,490,810 tokens
38,983,336,477 tokens
41,563,662,968 tokens
45,667,405,091 tokens
50,027,952,246 tokens
58,893,691,236 tokens
56,986,582,413 tokens
48,998,207,263 tokens
42,123,096,197 tokens
45,994,206,414 tokens
47,785,651,472 tokens
59,357,498,195 tokens
55,589,992,139 tokens
58,128,636,416 tokens
51,996,290,589 tokens
43,656,873,861 tokens
43,196,690,192 tokens
54,386,645,675 tokens
71,488,436,838 tokens
55,457,705,000 tokens
57,260,692,865 tokens
54,634,084,132 tokens
44,196,526,918 tokens
50,602,610,919 tokens
60,695,896,767 tokens
62,833,338,256 tokens
58,400,449,700 tokens
57,208,674,107 tokens
60,412,029,609 tokens
58,028,444,980 tokens
60,886,166,075 tokens
67,326,788,634 tokens
70,119,450,276 tokens
68,051,662,773 tokens
71,271,670,453 tokens
63,662,661,568 tokens
58,887,262,957 tokens
Daily observations · 89 days
| Date (UTC) | Reported tokens | Reported routes |
|---|---|---|
| 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 |
| Aug 15, 2026 | 49,407,478,743 | 1 |
| Aug 14, 2026 | 54,554,005,596 | 1 |
| Aug 13, 2026 | 88,309,998,870 | 1 |
| Aug 12, 2026 | 90,514,544,009 | 1 |
| Aug 11, 2026 | 86,793,779,422 | 1 |
| Aug 10, 2026 | 60,349,064,056 | 1 |
| Aug 9, 2026 | 62,601,543,555 | 1 |
| Aug 8, 2026 | 56,666,442,277 | 1 |
| Aug 7, 2026 | 62,261,223,176 | 1 |
| Aug 6, 2026 | 59,946,744,190 | 1 |
| Aug 5, 2026 | 58,317,628,475 | 1 |
| Aug 4, 2026 | 55,964,966,146 | 1 |
| Aug 3, 2026 | 58,380,676,115 | 1 |
| Aug 2, 2026 | 58,206,755,880 | 1 |
| Aug 1, 2026 | 59,832,944,881 | 1 |
| Jul 31, 2026 | 67,704,518,305 | 1 |
| Jul 30, 2026 | 60,257,543,548 | 1 |
| Jul 29, 2026 | 55,898,837,571 | 1 |
| Jul 28, 2026 | 57,046,179,599 | 1 |
| Jul 27, 2026 | 54,833,836,735 | 1 |
| Jul 26, 2026 | 47,150,857,085 | 1 |
| Jul 25, 2026 | 46,328,267,209 | 1 |
| Jul 24, 2026 | 54,956,549,011 | 1 |
| Jul 23, 2026 | 56,373,530,367 | 1 |
| Jul 22, 2026 | 59,735,936,886 | 1 |
| Jul 21, 2026 | 55,210,350,997 | 1 |
| Jul 20, 2026 | 50,749,767,126 | 1 |
| Jul 19, 2026 | 45,525,733,011 | 1 |
| Jul 18, 2026 | 47,768,892,422 | 1 |
| Jul 17, 2026 | 50,878,261,392 | 1 |
| Jul 16, 2026 | 48,291,474,713 | 1 |
| Jul 15, 2026 | 46,111,510,701 | 1 |
| Jul 14, 2026 | 45,717,012,237 | 1 |
| Jul 13, 2026 | 48,915,978,436 | 1 |
| Jul 12, 2026 | 40,527,579,540 | 1 |
| Jul 11, 2026 | 40,620,552,025 | 1 |
| Jul 10, 2026 | 50,126,368,594 | 1 |
| Jul 9, 2026 | 44,530,904,215 | 1 |
| Jul 8, 2026 | 45,658,252,754 | 1 |
| Jul 7, 2026 | 46,755,301,879 | 1 |
Source: OpenRouter (openrouter.ai/rankings), as of Oct 4, 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.
google/gemma-4-31b-itObserved - Context
- 262,144
- Maximum output
- 16,384
- Tokenizer
- Gemma
- Input
- image, text, video
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-04-02
https://openrouter.ai/api/v1google/gemma-4-31b-itgoogle/gemma-4-31b-it-20260402google/gemma-4-31B-itReasoning
- Required
- No
- Enabled by default
- No
- Default effort
- —
- Supported efforts
- —
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Default parameters
- top k
- 64
- top p
- 0.95
- temperature
- 1
google/gemma-4-31b-it:freeObserved - Context
- 262,144
- Maximum output
- 32,768
- Tokenizer
- Gemma
- Input
- image, text, video
- Output
- text
- Moderation
- No
- Added to OpenRouter
- 2026-04-02
https://openrouter.ai/api/v1google/gemma-4-31b-it:freegoogle/gemma-4-31b-it-20260402google/gemma-4-31B-itReasoning
- Required
- No
- Enabled by default
- No
- Default effort
- —
- Supported efforts
- —
Supported parameters
include_reasoningmax_tokensreasoningresponse_formatseedtemperaturetool_choicetoolstop_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 58 cataloged offers across 37 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: Yes. Structured output: Yes. Support can vary by endpoint.
Resources
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
fa9973480682 - ·
543f0b05f2db