Gemma 4 26B IT
Model Information
Display Name: Gemma 4 26B IT
API Model ID: google/gemma-4-26b-a4b-it
Category: Image To Text
Description: Gemma 4 26B IT is Google''s latest open-weight multimodal Mixture-of-Experts model, combining text reasoning, vision understanding, and agentic capabilities in a single efficient 26B parameter model with only 4B active at inference. **Key Features:** - 256K token context window - Multimodal: processes text, images, and video (up to 60 seconds) - Mixture-of-Experts architecture (25.2B total, 3.8B active) - Configurable thinking modes for advanced reasoning - Function calling and structured JSON outputs - Support for 35+ languages out-of-the-box, pre-trained on 140+ **Capabilities:** - Text generation, chat, and complex reasoning - Image understanding at variable aspect ratios and resolutions - Video processing and temporal reasoning - Code generation, completion, and debugging - Function/tool calling with agentic workflows - Document analysis and long-context retrieval **Best For:** - Cost-efficient multimodal applications - Long-document analysis (up to 256K tokens) - Agentic workflows and tool use - Vision + reasoning pipelines - Multilingual applications **Technical Specs:** - Architecture: Sparse Mixture-of-Experts (8 active / 128 total + 1 shared) - Total Parameters: 25.2B - Active Parameters: 3.8B per token - Layers: 30 - Sliding Window: 1024 tokens - Vocabulary: 262K tokens - Vision Encoder: ~550M parameters - License: Apache 2.0 **Benchmarks:** - MMLU Pro: 82.6% - AIME 2026: 88.3% - LiveCodeBench v6: 77.1% - Codeforces ELO: 1718 - MRCR v2 (128K, 8-needle): 44.1%
Context Window: 262,144 tokens
Max Output: 8,192 tokens
How to Use This Model
To use Gemma 4 26B IT via the HInow.ai API, use the model ID: google/gemma-4-26b-a4b-it
API Request Example (Chat/Text)
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "google/gemma-4-26b-a4b-it",
"messages": [
{"role": "user", "content": "Your message here"}
]
}
API Request Example (Image Generation)
POST https://api.hinow.ai/v1/images
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "google/gemma-4-26b-a4b-it",
"prompt": "Your image description here"
}
Pricing
- input: $0.18
- output: $0.585
- image: $0.015
Available Parameters
- temperature: Controls randomness (0-2). Higher = more creative, lower = more deterministic. Default: 0.7 (Options: 0, 0.3, 0.5, 0.7, 1.0, 1.5, 2.0)
- top_p: Nucleus sampling threshold (0-1). Default: 0.9 (Options: 0.1, 0.5, 0.7, 0.9, 0.95, 1.0)
- top_k: Limits sampling to top K tokens. Default: off (Options: 10, 20, 40, 50, 100)
- max_tokens: Maximum tokens to generate (1-8192). Default: 4096 (Options: 256, 512, 1024, 2048, 4096, 8192)
- repetition_penalty: Penalty for repeating tokens (0.01-5). Default: 1.0 (Options: 1.0, 1.1, 1.2, 1.5, 2.0)
- response_format: Output format for structured responses (Options: text, json_object, json_schema)
- stop: Up to 4 sequences where the API stops generating further tokens
Quick Reference
To use this model, set: "model": "google/gemma-4-26b-a4b-it"
Featured: No
Documentation: https://hinow.ai/models/google/gemma-4-26b-a4b-it
API Endpoint: https://api.hinow.ai/v1
