← Back to Directory

Gemma 4 31B

GOOGLE Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1433Chatbot Arena Verified
Max Context262,144Tokens
API Cost / 1M$0.49Blended Prompt + Completion

Model Capabilities

  • Coding & Logic
  • Fictional
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 (Prompt)$0.12 / 1M
Output Tokens (Completion)$0.37 / 1M

Pricing data via OpenRouter. Sync: 5/20/2026

Evaluate Competitors

VS Engine MatchupGemma 4 31B vs Arcee AI: Trinity Large ThinkingVS Engine MatchupGemma 4 31B vs StepFun: Step 3.5 FlashVS Engine MatchupGemma 4 31B vs MoonshotAI: Kimi K2.5VS Engine MatchupGemma 4 31B vs OpenAI: GPT Audio MiniVS Engine MatchupGemma 4 31B vs Qwen: Qwen Plus 0728VS Engine MatchupGemma 4 31B vs Meta: Llama 3.3 70B Instruct