Identity
- Status
- active
- Developer ID
google/gemma-4-E4B-it- Released
- Mar 2, 2026
- Version
- Gemma 4 E4B
- License
- apache-2.0
Google DeepMindGemma 4 E4B
Gemma 4 E4B is an instruction-tuned, open-weight Google Gemma 4 multimodal reasoning model.
- Token context
- 131K tokens
- Inputs
- Text, Image, Video, Audio
- Outputs
- Text
- Released
- Mar 2, 2026
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.020 | $0.10 | — | — | Sep 24, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 131K tokens
- Maximum output
- Unknown
- Total parameters
- Unknown
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image, Video, Audio
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- Yes
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, reasoning, structured outputs, tools
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
AliasesGemma 4 E4B, gemma-4-E4B-it, google/gemma-4-E4B-it
Explicit Unknowns
- Maximum output
- Tokenizer
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Gemma 4 E4BGoogle DeepMind | vs | Seed 2.1 TurboByteDance Seed | cross-developer peersimage, text, video |
Gemma 4 E4BGoogle DeepMind | vs |  Command A VisionCohere | cross-developer peersimage, text |
Gemma 4 E4BGoogle DeepMind | vs | Gemma 4 12BGoogle DeepMind | family variantsaudio, image, text, video |
Gemma 4 E4BGoogle DeepMind | vs | Gemma 4 26B A4BGoogle DeepMind | family variantsimage, text |
Gemma 4 E4BGoogle DeepMind | vs | Gemma 4 31BGoogle DeepMind | family variantsimage, text |
Gemma 4 E4BGoogle DeepMind | vs |  Muse Spark 1.1Meta | cross-developer peersaudio, image, text, video |
Gemma 4 E4BGoogle DeepMind | vs | Muse Spark 1.2Meta | cross-developer peersaudio, image, text, video |
Gemma 4 E4BGoogle DeepMind | vs |  GPT-4oOpenAI | cross-developer peersimage, text |
Gemma 4 E4BGoogle DeepMind | vs | GPT-4o MiniOpenAI | cross-developer peersimage, text |
Gemma 4 E4BGoogle DeepMind | vs | o3OpenAI | cross-developer peersimage, text |
Gemma 4 E4BGoogle DeepMind | vs |  Sonar Deep ResearchPerplexity | cross-developer peerstext |
Gemma 4 E4BGoogle DeepMind | vs | Sonar Reasoning ProPerplexity | cross-developer peerstext |
Questions
Gemma 4 E4B FAQs
What is Gemma 4 E4B?+
Gemma 4 E4B is an instruction-tuned, open-weight Google Gemma 4 multimodal reasoning model. It is developed by Google DeepMind and its current sourced lifecycle status is active.
What inputs and outputs does Gemma 4 E4B support?+
Gemma 4 E4B's current record lists Text, Image, Video, and Audio as input and Text as output.
How much context does Gemma 4 E4B support?+
The current record lists a 131K-token context window and does not report a maximum output length.
Is Gemma 4 E4B available through an API?+
Gemma 4 E4B is marked as API-available. The directly sourced provider records currently include Deepinfra and Together Ai.
How large is Gemma 4 E4B?+
The current record lists an unknown total parameter count and an unknown active parameter count. Its architecture is Gemma4ForConditionalGeneration.
What capabilities and tasks does Gemma 4 E4B support?+
Gemma 4 E4B's recorded capabilities are chat, generation, reasoning, structured outputs, and tools. Its supported tasks are image, reasoning, and text.
How much does Gemma 4 E4B cost through an API?+
The lowest directly sourced prices currently attached to Gemma 4 E4B are $0.020 per million input tokens through Deepinfra and $0.10 per million output tokens through Deepinfra. Prices are provider-specific and should be checked against each cited observation date.
Can Gemma 4 E4B be self-hosted?+
Gemma 4 E4B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Gemma 4 E4B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are Gemma 4 E4B, gemma-4-E4B-it, and google/gemma-4-E4B-it.
Which models can Gemma 4 E4B be compared with?+
The current compatible peer set includes Seed 2.1 Turbo, Command A Vision, Gemma 4 12B, Gemma 4 26B A4B, and Gemma 4 31B. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →