← Back to Directory

Gemma 4 31B

GOOGLE Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1433Chatbot Arena Verified
Max Context Limit262,144Max Out: 16,384 tokens
Prompt Caching44% OFF$0.05 / 1M cached
Standard API / 1M$0.43🧠 Deep Reasoner

Model Capabilities & Contract SLAs

  • Reasoning
  • Coding & Logic
  • Fictional
  • 🧠 Extended Test-Time Reasoning
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Granular Pricing Matrix

Input Tokens (Standard Prompt)$0.09 / 1M
⚡ Cached Input (Prompt Cache Read)44% OFF$0.05 / 1M
Output Tokens (Completion)$0.34 / 1M

Pricing data via OpenRouter. Sync: 10/2/2026

Evaluate Competitors

VS Engine MatchupGemma 4 31B vs OpenAI: GPT-6 LunaVS Engine MatchupGemma 4 31B vs OpenAI: GPT-6 Sol ProVS Engine MatchupGemma 4 31B vs Qwen: Qwen3.8 2.4T A95BVS Engine MatchupGemma 4 31B vs MoonshotAI: Kimi K2.7 CodeVS Engine MatchupGemma 4 31B vs Qwen: Qwen3.7 MaxVS Engine MatchupGemma 4 31B vs Arcee AI: Trinity Large Thinking