Gemma 4 31B (free)
GOOGLE Developer Architecture Profile
Intelligence (ELO)1439Chatbot Arena Verified
Max Context Limit262,144Max Out: 32,768 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1MFREE🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Reasoning
- Free Tier
- 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)Free / 1M
Output Tokens (Completion)Free / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupGemma 4 31B (free) vs Meituan: LongCat 2.0VS Engine MatchupGemma 4 31B (free) vs OpenAI: GPT-5.1VS Engine MatchupGemma 4 31B (free) vs Qwen: Qwen3 VL 235B A22B InstructVS Engine MatchupGemma 4 31B (free) vs Anthropic: Claude Sonnet 4VS Engine MatchupGemma 4 31B (free) vs OpenAI: GPT-6.1 SolVS Engine MatchupGemma 4 31B (free) vs OpenAI: GPT Terra Latest