Google: Gemma 4 31B
Analysis Summary
Google: Gemma 4 31B sits in the Professional tier on our leaderboard, ranked #38 of 525 published models on overall intelligence. At $0.130 input and $0.380 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and vision.
Editorial notes
Google's Gemma 4 31B is a strong open-weight model with solid reasoning, coding, and multimodal capability at very low cost, making it an excellent choice for businesses seeking capable performance without high API spend.
Assessed April 23, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
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..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemma 4 31B stack up?
Compare side-by-side with other professional models.
Model Information
| OpenRouter ID |
google/gemma-4-31b-it
|
| Provider | |
| Release Date | April 2, 2026 |
| Context Length | 262,144 tokens |
| Max Completion | 16,384 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.13 | $0.000130 |
| Output | $0.38 | $0.000380 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
