Gemma 4 31B IT
ActiveGemma 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...
Pricing
How much are you overpaying?
Enter your monthly spend on this model to see what the same workload could cost on cheaper alternatives.
Alternative models
Directional candidates based on stored listed rates and editorial scenario tags; validate quality and current terms before switching
Significant cost savings
Significant cost savings
Significant cost savings
Significant cost savings
Significant cost savings
Latest changes
Benchmarks
No benchmark data available.
⚡Gemma 4 31B IT Comparisons & Scenario Guides
❓Gemma 4 31B IT Frequently Asked Questions
How much does Gemma 4 31B IT cost per 1M tokens?▼
Gemma 4 31B IT is priced at $0.09 per 1M input tokens and $0.34 per 1M output tokens, with cached input at $0.05/1M on openrouter. Check provider terms before deployment.
What is the context window for Gemma 4 31B IT?▼
Gemma 4 31B IT supports up to 262,144 tokens context with a max completion limit of 16,384 tokens.
What are cost-saving alternatives to Gemma 4 31B IT?▼
ModelPriceLab automatically calculates cheaper alternatives in the same model class, showing monthly spend differences and migration guides.
Does this change your best option?
Check your models and usage for free. See the relevant official changes, estimated cost, and a practical next step.