Google: Gemma 4 31B
Analysis Summary
Gemma 4 31B is Google's dense 31-billion-parameter model, with an intelligence index of 29.4 and a coding index of 43.4, both meaningfully above the sparse 26B A4B sibling. The agentic index of 48.2 is more capable for multi-step tasks, and the model supports vision, video, tool use, and function calling across a 262K context window.
For businesses, Gemma 4 31B suits structured content generation, SEO workflows, coding assistance for lighter tasks, and tool-calling pipelines where multimodal input is needed. The instruction following score of 0.756 is strong for its tier, making it reliable for templated and structured output tasks.
At $0.12 input and $0.35 output per million tokens, it offers excellent price-performance for a benchmarked multimodal model. Teams needing a step up from the 26B A4B without moving to premium pricing will find it a practical choice.
Assessed July 10, 2026
Editorial notes
Gemma 4 31B from Google pairs vision, video, and tool use with a 262K context at $0.12 input per million tokens, offering a meaningful step up in reasoning and coding over the 26B A4B variant.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
DFO Verdict
Gemma 4 31B from Google pairs vision, video, and tool use with a 262K context at $0.12 input per million tokens, offering a meaningful step up in reasoning and coding over the 26B A4B variant.
Benchmark scores
Magenta = intelligence Ā· Ink = technical/agentic Ā· Cyan = content & long-context Ā· Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.
29.4 Intelligence IndexĀ·43.4 Coding IndexĀ·48.2 Agentic Index
How Google: Gemma 4 31B compares
Google: Gemma 4 31B ranks #96 of 393 AI models we track for overall intelligence, #51 of 157 for coding, #83 of 300 for agentic tasks. Its 262K-token context window is larger than 80% of the models we list. At $0.12 per million input tokens it is cheaper than 62% of comparable models.
Dark bar = input Ā· light bar = output, scaled to the priciest peer.
1M tokens ā 8 full-length novels or ~2,500 pages of business documents in a single request.
Strongest on value. The pulled-in intelligence corner is the trade-off, and if the shape matters more than the price, this is your model.
Compare shapes side-by-side āPricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.12 | $0.000120 |
| Output | $0.37 | $0.000370 |
What would Google: Gemma 4 31B cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 612 models ā Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save Google: Gemma 4 31B for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout Google: Gemma 4 31B
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..
Embed this ranking
Frequently asked questions about Google: Gemma 4 31B
How much does Google: Gemma 4 31B cost?
Google: Gemma 4 31B costs $0.12 per million input tokens and $0.37 per million output tokens.
What is the context window of Google: Gemma 4 31B?
Google: Gemma 4 31B has a context window of 262,144 tokens (262K).
Is Google: Gemma 4 31B good for coding?
On our coding benchmark index, Google: Gemma 4 31B ranks #51 of 157 models, placing it in the broader range of the field for code generation and debugging.
What can Google: Gemma 4 31B do?
Google: Gemma 4 31B supports image/vision input, tool use, and function calling.
Who created Google: Gemma 4 31B?
Google: Gemma 4 31B is developed by Google and was released on April 2, 2026.
