Inference availability
Providers Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.
Report a price
Providers offering Gemma 3n E4B IT
Provider Provider model ID Context Max output Input Output Cache read Capabilities Docs
N Nvidia google/gemma-3n-e4b-it128K
4.096K
— — — Tools JSON Docs ↗
Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.
Specification
Capabilities Recorded from the source catalog and provider listings.
?
Reasoning
Unknown
?
Tool calling
Unknown
?
Structured output
Unknown
✓
Attachments
Yes
✓
Vision input
Yes
✓
Open weights
Yes
Model family gemma
Knowledge cutoff 2024-06
License Gemma Terms of Use
Release date 2025-06-26
Model ID google/gemma-3n-e4b-it
Weights:
Hugging Face ↗
Published evaluations
Benchmarks Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.
Benchmark registry
Coding Index
#213 of 214
2.7
median 49.3
81.6
Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.
Cost against capability
Price and performance Listed input price plotted against Coding Index, the benchmark with the widest published coverage that this model appears in.
0
43
86
$0.01
$0.1
$1
$10
Nova 2 Lite — $0.3/M, score 23.0
Claude Fable 5 — $10/M, score 76.5
Anthropic: Claude Fable 5.1 — $10/M, score 81.6
Anthropic: Claude Fable 5.1 (batch) — $5/M, score 81.6
Anthropic: Claude Fable 5 (batch) — $5/M, score 76.5
Anthropic: Claude Haiku 4.5 — $1/M, score 43.9
Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 43.9
Anthropic: Claude Opus 4.7 — $5/M, score 73.6
Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 73.6
Anthropic: Claude Opus 4.8 — $5/M, score 74.3
Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 74.3
Claude Opus 5 — $5/M, score 78.0
Anthropic: Claude Opus 5 (batch) — $2.5/M, score 78.0
Anthropic: Claude Sonnet 4 — $3/M, score 37.6
Anthropic: Claude Sonnet 4.5 — $3/M, score 52.1
Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 52.1
Anthropic: Claude Sonnet 4.6 — $3/M, score 63.0
Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 63.0
Claude Sonnet 5 — $2/M, score 71.5
Anthropic: Claude Sonnet 5 (batch) — $1/M, score 71.5
Trinity Large Thinking — $0.25/M, score 25.8
Command A — $2.5/M, score 27.8
DeepSeek V3 0324 — $0.2/M, score 21.2
DeepSeek-R1 — $0.58/M, score 24.6
DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 43.5
DeepSeek V3.2 — $0.209/M, score 44.2
DeepSeek V4 Flash — $0.15/M, score 52.0
DeepSeek V4 Flash 0731 — $0.035/M, score 69.1
DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 69.1
DeepSeek V4 Flash Vision Exp — $0.15/M, score 65.0
DeepSeek V4 Pro — $0.66/M, score 59.4
DeepSeek V4 Pro 0813 — $0.132/M, score 68.8
DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 68.8
Gemini 2.5 Pro — $1.25/M, score 33.3
Google: Gemini 2.5 Pro (batch) — $0.625/M, score 33.3
Gemini 3.1 Flash Lite Preview — $0.25/M, score 34.7
Gemini 3.1 Pro Preview — $2/M, score 68.8
Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 68.8
Gemini 3.5 Flash — $1.5/M, score 70.1
Gemini 3.5 Flash Lite — $0.3/M, score 49.3
Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 49.3
Google: Gemini 3.5 Flash (batch) — $0.75/M, score 70.1
Gemini 3.6 Flash — $0.75/M, score 69.2
Google: Gemini 3.6 Flash (batch) — $0.375/M, score 69.2
Gemini 3.7 Flash — $0.75/M, score 71.5
Google: Gemini 3.7 Flash (batch) — $0.375/M, score 71.5
Gemini 3.8 Flash — $0.75/M, score 76.3
Google: Gemini 3.8 Flash (batch) — $0.375/M, score 76.3
Gemma 3 12B IT — $0.04/M, score 5.8
Gemma 3 27B IT — $0.08/M, score 10.1
Gemma 3 4B IT — $0.04/M, score 2.7
Gemma 4 26B A4B IT — $0.042/M, score 39.3
Gemma 4 31B IT — $0.1/M, score 43.4
Google: Gemma 4 31B (batch) — $0.39/M, score 43.4
IBM: Granite 4.1 8B — $0.05/M, score 9.5
IBM: Granite 4.2 8B — $0.06/M, score 22.4
Mercury 2 — $0.25/M, score 31.1
inclusionAI: Ling-2.6-flash — $0.01/M, score 25.3
Ling 3.0 Flash — $0.021/M, score 50.6
Ling 3.0 Flash Fin — $0.075/M, score 55.6
Ling 3.0 Flash VL — $0.06/M, score 57.0
inclusionAI: Ring-2.6-1T — $0.075/M, score 42.8
Kwaipilot: KAT-Coder-Pro V2 — $0.3/M, score 59.5
LongCat-2.0 — $0.3/M, score 45.3
Meta: Llama 3.1 8B Instruct — $0.05/M, score 5.4
Meta: Llama 3.3 70B Instruct — $0.1/M, score 11.9
Meta: Llama 4 Maverick — $0.188/M, score 16.3
Meta: Llama 4 Scout — $0.1/M, score 8.2
Muse Glimmer 30B — $0.2/M, score 49.0
Muse Spark 1.1 — $1.25/M, score 71.3
Muse Spark 1.2 — $1.25/M, score 72.2
Muse Spark 1.3 — $1.25/M, score 75.8
MiniMax: MiniMax M2.7 — $0.3/M, score 52.6
MiniMax: MiniMax M3 — $0.3/M, score 58.6
MiniMax: MiniMax M3 (batch) — $0.3/M, score 58.6
Mistral: Devstral 2 2512 — $0.4/M, score 31.3
Mistral: Ministral 3 14B 2512 — $0.2/M, score 14.4
Mistral: Ministral 3 3B 2512 — $0.1/M, score 4.8
Mistral: Ministral 3 8B 2512 — $0.15/M, score 9.7
Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 9.7
Mistral: Mistral Large 3 2512 — $0.5/M, score 20.1
Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 20.1
Mistral: Mistral Medium 3.5 — $1.5/M, score 46.9
Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 46.9
Mistral: Mistral Medium 3.1 — $0.4/M, score 20.5
Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 20.5
Mistral: Mistral Small 4 — $0.15/M, score 26.6
Mistral: Mistral Small 4 (batch) — $0.075/M, score 26.6
Kimi K2 Thinking — $0.4/M, score 21.0
Kimi K2.5 — $0.375/M, score 46.8
Kimi K2.6 — $0.95/M, score 61.8
Kimi K2.7 Code — $0.95/M, score 60.8
MoonshotAI: Kimi K2.7 Code (batch) — $0.475/M, score 60.8
Kimi K3 — $3/M, score 76.2
MoonshotAI: Kimi K3 (batch) — $2.28/M, score 76.2
Nex-N2-Pro — $0.5/M, score 59.1
Nemotron 3 Nano 30B A3B — $0.05/M, score 14.4
Nemotron 3 Super 120B A12B — $0.05/M, score 37.7
Nemotron 3 Ultra 550B A55B — $0.1/M, score 49.3
NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 49.3
Nemotron 3.5 Lightning 30B A3B — $0.025/M, score 26.8
GPT-3.5-turbo — $0.5/M, score 10.7
OpenAI: GPT-3.5 Turbo (batch) — $0.25/M, score 10.7
GPT-4 — $30/M, score 13.1
GPT-4 Turbo — $10/M, score 21.5
OpenAI: GPT-4 Turbo (batch) — $5/M, score 21.5
GPT-4.1 mini — $0.4/M, score 20.2
OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 20.2
GPT-4.1 nano — $0.1/M, score 11.1
OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 11.1
GPT-4o (2024-05-13) — $5/M, score 24.2
GPT-4o mini — $0.15/M, score 11.4
OpenAI: GPT-4o-mini (batch) — $0.075/M, score 11.4
GPT-5 — $1.25/M, score 37.8
GPT-5 Mini — $0.25/M, score 15.6
OpenAI: GPT-5 Mini (batch) — $0.125/M, score 15.6
GPT-5.1 — $1.25/M, score 49.4
OpenAI: GPT-5.1 (batch) — $0.625/M, score 49.4
GPT-5.4 — $2.5/M, score 71.1
GPT-5.4 mini — $0.75/M, score 56.1
OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 56.1
GPT-5.4 nano — $0.2/M, score 56.1
OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 56.1
OpenAI: GPT-5.4 (batch) — $1.25/M, score 71.1
GPT-5.5 — $5/M, score 74.9
OpenAI: GPT-5.5 (batch) — $2.5/M, score 74.9
GPT-5.6 Luna — $0.2/M, score 71.4
OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 71.4
GPT-5.6 Sol — $4/M, score 77.4
OpenAI: GPT-5.6 Sol (batch) — $2/M, score 77.4
GPT-5.6 Terra — $2/M, score 76.7
OpenAI: GPT-5.6 Terra (batch) — $1/M, score 76.7
OpenAI: GPT-5 (batch) — $0.625/M, score 37.8
GPT-6 Astra — $10/M, score 76.9
OpenAI: GPT-6 Astra (batch) — $5/M, score 76.9
GPT OSS 120B — $0.03/M, score 30.4
OpenAI: gpt-oss-120b (batch) — $0.03/M, score 30.4
GPT OSS 20B — $0.018/M, score 20.7
OpenAI: gpt-oss-20b (batch) — $0.024/M, score 20.7
o1 — $15/M, score 39.7
OpenAI: o1 (batch) — $7.5/M, score 39.7
OpenAI: o3 Mini High — $1.1/M, score 16.3
OpenAI: o3 Mini High (batch) — $0.55/M, score 16.3
Qwen: Qwen3 14B — $0.12/M, score 13.8
Qwen: Qwen3 235B A22B Thinking 2507 — $0.45/M, score 22.1
Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 12.1
Qwen: Qwen3 32B — $0.08/M, score 15.3
Qwen: Qwen3 8B — $0.117/M, score 9.0
Qwen: Qwen3 Coder Next — $0.12/M, score 36.2
Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 17.4
Qwen: Qwen3.5-122B-A10B — $0.4/M, score 43.3
Qwen: Qwen3.5-35B-A3B — $0.14/M, score 37.0
Qwen: Qwen3.5 397B A17B — $0.5/M, score 48.2
Qwen: Qwen3.5-9B — $0.17/M, score 23.5
Qwen: Qwen3.5-9B (batch) — $0.17/M, score 28.7
Qwen: Qwen3.6 27B — $0.25/M, score 53.7
Qwen: Qwen3.6 35B A3B — $0.1/M, score 41.9
Qwen: Qwen3.6 Plus — $0.325/M, score 54.5
Qwen: Qwen3.7 Max — $1.475/M, score 66.0
Qwen: Qwen3.7 Plus — $0.32/M, score 55.9
Qwen: Qwen3.7 Plus (batch) — $0.23/M, score 55.9
Qwen: Qwen3.8 2.4T A95B — $2/M, score 71.9
Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 71.9
Qwen: Qwen3.8 27B — $0.2/M, score 68.1
Qwen: Qwen3.8 Max — $2/M, score 68.9
Qwen: Qwen3.8 Max (0902) — $2/M, score 76.2
Step 3.7 Flash — $0.202/M, score 39.6
Hy3 preview — $0.18/M, score 58.8
Inkling — $1/M, score 52.1
Inkling Small — $0.3/M, score 52.9
Thinking Machines: Inkling Small (batch) — $0.5/M, score 52.9
Thinking Machines: Inkling (batch) — $1/M, score 52.1
Upstage: Solar Pro 3 — $0.15/M, score 16.2
Solar Pro 4 — $0.3/M, score 52.7
SpaceXAI: Grok 4.3 — $1.25/M, score 42.2
SpaceXAI: Grok 4.3 (batch) — $1/M, score 42.2
SpaceXAI: Grok 4.5 — $2/M, score 72.4
SpaceXAI: Grok 4.6 — $2/M, score 76.8
SpaceXAI: Grok Build 0.1 — $1/M, score 51.5
MiMo-V2.5 — $0.14/M, score 56.8
MiMo-V2.5-Pro — $0.435/M, score 60.2
Z.ai: GLM 4.6 — $0.55/M, score 45.8
Z.ai: GLM 4.7 — $0.54/M, score 45.3
Z.ai: GLM 5.1 — $1.4/M, score 55.8
Z.ai: GLM 5.2 — $0.034/M, score 68.8
Z.ai: GLM 5.2 (batch) — $0.7/M, score 68.8
Z.ai: GLM 5.3 — $0.079/M, score 74.8
Z.ai: GLM 5.3 Flash — $0.15/M, score 71.5
Z.ai: GLM 5.3 Flash (batch) — $0.05/M, score 71.5
Z.ai: GLM 5.3 (batch) — $0.45/M, score 74.8
Input price per million tokens (log scale)
Index
The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.
Catalog activity
Change log Field-level changes detected between successful source imports.
Full change log No changes recorded This record has not changed within the retained import history.
Provenance
Sources & verification Every figure on this page traces back to one of these records.
Methodology
Last verified Oct 24, 2026
Status Source-linked
Confidence Medium
Catalog source Models.dev
Public API
Use this record Fetch the complete source-linked model record. No key, no account, no rate-limited tier.
API documentation
Endpoint Copy
GET https://modelbench.lol/api/v1/models/google/gemma-3n-e4b-itcurl Copy
curl "https://modelbench.lol/api/v1/models/google/gemma-3n-e4b-it"
Common questions
Frequently asked questions Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.
What is Gemma 3n E4B IT?
Efficient on-device Gemma 3n model for text, image, and audio understanding. It is published by Google and catalogued here from Models.dev.
What is the context length of Gemma 3n E4B IT?
Gemma 3n E4B IT accepts up to 32.768K tokens of context and returns up to 32.768K output tokens.
Does Gemma 3n E4B IT support tool calling and structured output?
Provider catalogs list support for image input.
Which providers serve Gemma 3n E4B IT?
1 provider list this model: Nvidia.
Are the weights for Gemma 3n E4B IT open?
Yes. The weights are published and downloadable from Hugging Face under the Gemma Terms of Use license.
When was Gemma 3n E4B IT released?
The catalog records a release date of 2025-06-26, last verified Oct 24, 2026.
Nvidia