14.7
Intelligence Index
Above 50% of 46 other free models
Go
Google: Gemma 4 31B
Free allowance
Up to10,000requests / day
via NVIDIA
- 40 requests / minute
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...
- Input
- image
- text
- video
- Output
- text
- Video understanding
Providers
Available through 3 free providers. Use the model ID and API settings below to connect.
* The provider match may differ from this model. Check its docs for details.
Benchmarks
Compare scores and explore results by category.
43.4
Coding Index
Above 51% of 33 other free models
4.2
Agentic Index
Above 46% of 28 other free models
Bars show scores from other free models on this site. The marker shows this model’s score. Comparisons include only models with a score for that index.
Scores from Artificial AnalysisFrequently asked questions
Free access, setup, and what to expect.
Gemma 4 31B is available with up to 10,000 requests / day free through NVIDIA. Additional limits apply at the same time: 40 requests / minute. Free allowances can change. Check the Gemma 4 31B provider limits before you start.
To use Gemma 4 31B, choose one of the listed Gemma 4 31B API providers and follow the provider’s account and API-key setup guide. Copy the Gemma 4 31B model ID and connection settings for your chosen provider into your app or API client. Model IDs can differ between providers. API requests go directly to the provider; Free Models is a comparison site.
Gemma 4 31B accepts image, text, and video as listed input formats. Listed output formats include text. Image or audio input support does not imply image or audio generation. Check the chosen provider’s Gemma 4 31B documentation for supported file types and request formats.
Gemma 4 31B has a listed context window of 262K tokens. Tokens are small pieces of content rather than a word count. Instructions, conversation history, and other inputs use context space, and the response also needs room. The maximum output length for Gemma 4 31B may be smaller than the context window and can vary by provider.
Gemma 4 31B has both reasoning and tool calling listed as supported capabilities. Reasoning enables additional processing for complex problems. Tool calling allows a model to request functions that your app executes. Check the chosen provider’s documentation for capability availability and setup.
Review the listed Gemma 4 31B benchmark results to compare performance on measured tasks. Compare scores within the same benchmark: coding indexes, Elo ratings, and win rates measure different things. The index comparison charts include only scored free models listed on Free Models. Evaluate Gemma 4 31B on examples from your own task alongside context size and provider limits.