Gemma 4 31B
Gemma 4 31B is a multimodal text generation model from Google with a 262,144-token context window.
Google
DeepInfraMultimodal reasoning from Google's Gemma 4 series
Gemma 4 31B is an instruction-tuned large language model developed by Google, released in April 2026 as part of the Gemma 4 model family. It supports both text and image inputs, making it a multimodal model capable of processing visual and textual information together. With 31 billion parameters, it is served through DeepInfra and is available on MindStudio under the model ID google/gemma-4-31B-it.
The model features a 262,144-token context window, allowing it to process long documents, extended conversations, and large codebases in a single pass. It supports a maximum response size of 16,384 tokens and is tagged for reasoning and multimodal tasks. Gemma 4 31B is well suited for use cases that require understanding of both images and text, long-context comprehension, and multi-step reasoning.
What Gemma 4 31B supports
Long Context Window
Processes up to 262,144 tokens in a single request, enabling analysis of lengthy documents, codebases, or extended conversations without truncation.
Image Understanding
Accepts image inputs alongside text, allowing the model to answer questions about, describe, or reason over visual content.
Multi-Step Reasoning
Tagged for reasoning tasks, the model can work through complex, multi-step problems across domains such as logic, analysis, and question answering.
Text Generation
Generates up to 16,384 tokens per response, supporting tasks like summarization, drafting, explanation, and structured content creation.
Instruction Following
Fine-tuned as an instruction-following model (the -it suffix), making it responsive to direct prompts and system-level instructions.
Ready to build with Gemma 4 31B?
Get Started FreeCommon questions about Gemma 4 31B
What is the context window size for Gemma 4 31B?
Gemma 4 31B supports a context window of 262,144 tokens, which allows it to process very long documents or conversations in a single request.
Does Gemma 4 31B support image inputs?
Yes. The model supports image inputs in addition to text, making it a multimodal model capable of reasoning over visual and textual content together.
What is the maximum response length?
The model can generate up to 16,384 tokens in a single response.
Who developed Gemma 4 31B and when was it released?
Gemma 4 31B was developed by Google and released in April 2026 as part of the Gemma 4 model family.
What is the knowledge cutoff for Gemma 4 31B?
A specific knowledge cutoff date is not listed in the available metadata. Google has not publicly confirmed a precise training data cutoff for this model at this time.
Is pricing available for Gemma 4 31B on MindStudio?
Published pricing is not listed in the current metadata. You can check MindStudio's model catalog or DeepInfra's pricing page for the latest rate information.
Parameters & options
Explore similar models
GoogleGemini 3.1 Pro
Gemini 3.1 Pro is a multimodal text generation model from Google with a 1,048,576-token context window.
GoogleGemini 3.7 Flash
Gemini 3.7 Flash is a text generation model from Google with a 1,048,576-token context window and configurable thinking levels.
GoogleGemma 3.2
Gemma 3.2 is a 27-billion-parameter text generation model from Google with a 128,000-token context window.
AnthropicClaude 5 Sonnet
Claude 5 Sonnet is Anthropic's flagship text and vision model with a 1,000,000-token context window and extended reasoning.
OpenAIGPT-5.5
GPT-5.5 is a multimodal text generation model from OpenAI with a 1,000,000-token context window and adjustable reasoning effort.
DeepSeekDeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a text generation model from DeepSeek with a 1,048,576-token context window and configurable reasoning effort.
Start building with Gemma 4 31B
No API keys required. Create AI-powered workflows with Gemma 4 31B in minutes — free.