LLM Reference

Gemma 4 31B

Released
2026-03-31
Last refreshed
2026-06-29
Status
Researched 29d ago
Open sourceCommercial use: permittedMultimodalRAGAgentsLong contextVisionJSON / Tool use

Gemma 4 31B is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 256k context window
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Gemma 4
Released
2026-03-31
Context
256k
Parameters
31B
Knowledge cutoff
2025-01
Openness
Open source
License
Apache 2.0OSI-approvedCommercial use: permitted
Weights
Available
Code
Unknown
Created by
Google DeepMindGoogle DeepMind

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$0.400
Input / 1M
$0.140

Cheapest of 2 routes · Vercel AI Gateway

Providers(2)
Vercel AI GatewayAWS Bedrock
View 2 provider routes

About

Dense 31B model bridging the gap between server-grade performance and local execution. Ranks #3 on Arena AI leaderboard. Supports text, image, and video inputs with advanced reasoning.

Gemma 4 31B is an open-source model in the Gemma 4 family. The structured metadata tracks a 256k-token context window, multimodal input, and function calling. This page tracks provider routes through Vercel AI Gateway and AWS Bedrock, with the cheapest tracked route listed at $0.14 input and $0.4 output per 1M tokens. Headline tracked benchmarks include Google-Proof Q&A 85.7, MMMU Pro 76.9, and SWE-rebench 41.6.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 2

Compare API pricing across 2 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Vercel AI Gateway$0.140$0.400
Serverless
AWS Bedrock--
ServerlessPartial

Available via routers & gateways(1)

Amazon Bedrock Intelligent Prompt Routing

Router

AWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.

PassthroughAWS Bedrock

Capabilities

VisionMultimodalFunction Calling

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Google-Proof Q&A85.7diamondhttps://artificialanalysis.ai/leaderboards/models
MMMU Pro76.9LLM-Stats aggregatorhttps://llm-stats.com/benchmarks/mmmu-pro
SWE-rebench41.6pass@1 (best of 5 runs)https://swe-rebench.com/leaderboard

Migration checks

No linked migration route is available for this model yet.

Frequently asked questions

What is the context window of Gemma 4 31B?

Gemma 4 31B has a context window of 256k tokens.

How much does Gemma 4 31B cost?

Gemma 4 31B is available at $0.14/1M input tokens through Vercel AI Gateway.

When was Gemma 4 31B released?

Gemma 4 31B was released on 2026-03-31.

Which providers offer Gemma 4 31B?

Gemma 4 31B is available from 2 providers: Vercel AI Gateway, AWS Bedrock.

What benchmarks has Gemma 4 31B been tested on?

Gemma 4 31B has been evaluated on 3 benchmarks, including Google-Proof Q&A, MMMU Pro, SWE-rebench.