Gemma 4 31B

Tool callingStructured outputReasoningImage input

Model card Hugging Face Launch post Website Docs

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

Context: 262K
Released: 6mo ago
Parameters: 32.7B
Input / 1M tokens: $0.20
Output / 1M tokens: $0.40

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
GPQA diamond	75.8% Epoch AI · gemma-4-31b-it_minimal Reasoning effort: minimal Epoch AI evaluation
OTIS Mock AIME 2024-2025	73.3% Epoch AI · gemma-4-31b-it_minimal Reasoning effort: minimal Epoch AI evaluation
SimpleQA Verified	10.4% Epoch AI · gemma-4-31b-it Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: Google DeepMind
Model family: Gemma
Type: Language model
Predecessor: —
Successor: —
Released: April 2, 2026
Model ID: google/gemma-4-31b-it
Openness: Open weights
License: —
Parameters: 32.7B
Architecture: gemma4
Families: gemma4
Input modalities: image, text, video
Output modalities: text
Modality: text+image+video->text
Native context: 262K
Tokenizer: Gemma
Max output tokens: 16K
Hugging Face: google/gemma-4-31B-it
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: google/gemma-4-31b-it
Source family: gemma
Last updated: 2026-04-02
Model context: 262K
Model output limit: 33K
Open weights: Yes
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Downloadable weights

Hugging Face

Complete source record (JSON)

{
  "id": "google/gemma-4-31b-it",
  "name": "Gemma 4 31B IT",
  "description": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning",
  "family": "gemma",
  "last_updated": "2026-04-02",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 262144,
    "output": 32768
  },
  "release_date": "2026-04-02",
  "open_weights": true,
  "weights": [
    {
      "label": "Hugging Face",
      "url": "https://huggingface.co/google/gemma-4-31B-it"
    }
  ]
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
DeepInfra	deepinfra/turbo	262K	$0.09	$0.34	$0.05	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
CoreWeave	coreweave/fp4	262K	$0.10	$0.34	$0.10	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Chutes	chutes/fp4	131K	$0.12	$0.37	$0.01	—	98.96%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Venice	venice/fp4	256K	$0.12	$0.36	$0.09	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Crusoe	crusoe/bf16	262K	$0.14	$0.40	$0.14	—	97.77%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Friendli	friendli	262K	$0.14	$0.40	—	—	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Novita	novita/bf16	262K	$0.14	$0.40	—	—	83.13%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Parasail	parasail/fp8	262K	$0.15	$0.40	$0.06	—	99.93%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
DeepInfra	deepinfra/fp8	262K	$0.20	$0.40	—	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Io Net	io-net	262K	$0.36	$1.09	$0.18	—	96.17%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
SambaNova	sambanova	131K	$0.38	$1.15	—	—	58.95%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
ModelRun	modelrun/fp4	262K	$0.75	$1.00	$0.20	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
SiliconFlow	siliconflow/fp8	262K	$0.75	$1.00	$0.25	—	97.34%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

Gemini app/web

Google SynthID text watermarking

Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.

Official explanation

Deployment graph

Can I run this?

Vertical Tabs only shows compatibility when it has structured evidence tying this exact model to hardware, runtime, quantization, memory use, and observed performance.

Browse hardware