Question 1

What is Gemma 4 31B?

Accepted Answer

Gemma 4 31B is a model from Google Gemini AI, released on Oct 1, 2026. Gemma 4 31B is available on the Respan AI Gateway for production LLM workloads. Up to 33K context window.

Question 2

How much does Gemma 4 31B cost?

Accepted Answer

On the Respan gateway, input starts at $0.30 per 1M tokens on Prism, and output starts at $0.40 per 1M tokens on Prism, after gateway discounts.

Question 3

Which providers serve Gemma 4 31B on Respan?

Accepted Answer

Gemma 4 31B is served by Prism.

Question 4

What is Gemma 4 31B's context window?

Accepted Answer

Gemma 4 31B accepts up to 33K tokens of context.

Question 5

How do I use Gemma 4 31B with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "gemma-4-31b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

Where does Gemma 4 31B rank on the Respan Index?

Accepted Answer

Gemma 4 31B scores 16.8 out of 100 on the Respan Index v1.1, ranking #113 of 138 models. By category: Coding 8.4, Agents 13.7 (estimated), Reasoning 11.1, Knowledge & language 10.8, and Human preference 49.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 7

How does Gemma 4 31B score on benchmarks?

Accepted Answer

Gemma 4 31B has 14 published benchmark scores, including LiveCodeBench v6 80%, GPQA Diamond 84.3%, and AIME 2026 (no tools) 89.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Gemma 4 31B

Providers

Pricing

Cost by volume

Benchmarks

Respan Index

Certified where it counts.

Coding2

Reasoning4

Math2

Knowledge2

Arena3

Other1

Apps

Gemma 4 31B FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.