Gemma 4 31B (batch)
Gemma 4 31B · Batch tier (Batch)
Asynchronous batch tier: discounted offline batch requests with high throughput and relaxed latency — ideal for large-scale non-real-time workloads.
Best for: Large-scale offline inference, cost-sensitive batch jobs, backfills
This page covers the Gemma 4 31B Batch 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
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：235.9K
- Tokenizer：Gemma
- Released：2026-04-02
Token pricing
- Input price：$0.390 / 1M tokens
- Output price：$0.970 / 1M tokens
- Blended price：$0.535 / 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.（≈ $0.0078/call）
- Vision Understanding & Generation：Recognize data trends in charts, OCR scanned docs, analyze photos and produce structured reports.（≈ $0.0058/call）
- Chat & Support：FAQ auto-response, multi-turn dialogue, emotion detection — e-commerce, finance, gov.（≈ $0.0019/call）
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.
- 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 (batch)? Input price $0.390 / 1M tokens, output price $0.970 / 1M tokens, blended about $0.535 / 1M tokens. Refer to Google’s official page for the exact rate.
- What context window does Gemma 4 31B (batch) support? Context window is 262.1K, max output about 235.9K, suitable for long documents, multi-turn chat and complex reasoning.
- What scenarios is Gemma 4 31B (batch) best for? Based on its capability and pricing, Gemma 4 31B (batch) fits best: Deep Reasoning & Analysis, Vision Understanding & Generation, Chat & Support. See the Use Cases section for details and cost estimates.
- What input/output modalities does Gemma 4 31B (batch) support? Supports Image, Text, Video modality.
- Is Gemma 4 31B (batch) a free model? Gemma 4 31B (batch) is billed per token, not a free model.
- Which provider offers Gemma 4 31B (batch)? Gemma 4 31B (batch) is offered by Google.
More models from Google
Full info：Gemma 4 31B (batch)