Skip to content

Gemma 4 31B - Free Multimodal Model on OpenRouter, 262K Context

Gemma 4 31B is completely free: $0/M input tokens, $0/M output tokens.

Model Information

AttributeValue
Context length262,144 tokens
Max output32,768 tokens
Input price$0 / 1M tokens
Output price$0 / 1M tokens
ProviderGoogle
StatusFree

Description

Gemma 4 31B Instruct is a 30.7B dense multimodal model from Google DeepMind that accepts text and image input. It offers a 256K token context window and configurable thinking/reasoning modes.

Usage Example

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-31b-it:free",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Related Links

📚 Related Free Models

These models are also available for $0 on OpenRouter. Choose by context length and modality.

ModelContextDescription
Ling 3.2 Flash1MLing 3.2 Flash is inclusionAI’s hybrid reasoning model
Particle-11MParticle-1 is Particle AI’s agentic coding model,
ERNIE 5.5 Flash1MBaidu’s ERNIE 5.5 Flash Preview free model has 280B
LFM3 1.7B262KLiquid AI’s compact 1.7B text model with 262K context,
Recursive Flint262KRecursive’s 40B total / 2.5B active MoE model built for
Dots3 Note512KDots3-Note Preview is Dots Studio’s MoE model with 280B
Gemma 4 26B A4B - Free MoE Model on262KGemma 4 26B A4B is Google DeepMind’s multimodal MoE model
Lyria 3 Clip1MGoogle’s music clip generation model produces 30-second

📋 View all OpenRouter free models →

🔗 Site Navigation

Last updated on · Source: OpenRouter official documentation and pricing pages. Quotas and prices may change at any time.