Gemma 4 31B (free)
Gemma 4 31B · Free tier (Free)
Free tier: zero-cost access to try the model with limited quota — great for prototyping and light use.
Best for: Dev testing, light trials, low-frequency calls
This page covers the Gemma 4 31B Free tier, sharing the underlying model capability with its real-time standard tier; the main difference is in billing mode and invocation method. See the Gemma 4 31B standard real-time tier.
Provider：Google · Free
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...
Key specs
- Context：262.1K
- Max output：32.8K
- Tokenizer：Gemma
- Released：2026-04-02
Token pricing
- Input price：Free / 1M tokens
- Output price：Free / 1M tokens
- Blended price：Free / 1M tokens
Modalities
Image, Text, Video
Use Cases
- Deep Reasoning & Analysis：Process long legal docs, academic papers, financial reports; multi-hop reasoning and evidence-chain tracing across huge contexts.（Free）
- Vision Understanding & Generation：Recognize data trends in charts, OCR scanned docs, analyze photos and produce structured reports.（Free）
When to pick this model
Signals derived from public pricing and spec fields — not a benchmark. Validate with official docs and your own eval.
- Low input + output price: solid fit for high-frequency calls and batch processing.
- Low blended price: budget-friendly for fleet-scale deployment.
- Long max output (>=30K tokens): strong fit for deep report / essay / document-drafting workflows.
- Multimodal (text+image): fit for image captioning, OCR, chart QA, vision-grounded reasoning.
- Video input support: fit for video understanding, frame QA, content moderation.
FAQ
- What is the token pricing of Gemma 4 31B (free)? Input price Free / 1M tokens, output price Free / 1M tokens, blended about Free / 1M tokens. Refer to Google’s official page for the exact rate.
- What context window does Gemma 4 31B (free) support? Context window is 262.1K, max output about 32.8K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Gemma 4 31B (free) best for? Based on its capability and pricing, Gemma 4 31B (free) fits best: Deep Reasoning & Analysis, Vision Understanding & Generation. See the Use Cases section for details and cost estimates.
- What input/output modalities does Gemma 4 31B (free) support? Supports Image, Text, Video modality.
- Is Gemma 4 31B (free) a free model? Yes, Gemma 4 31B (free) is free to use, good for budget-sensitive or prototyping scenarios.
- Which provider offers Gemma 4 31B (free)? Gemma 4 31B (free) is offered by Google.
More models from Google
Full info：Gemma 4 31B (free)