Largest denso abierto modelo de razonamiento en el Gemma 4 series con 262K contexto y nativo cadena de pensamiento.
Technical Specifications
- Provider
- Category
- open-source
- Release Date
- 2026-04
- Batch API Discount
- Standard rate
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- models/gemma-4-31b
- Supported SDK & API Protocol
- Google Gemini API (generateContent) + OpenAI-Compatible SDK
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2028+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Free across full context window (only KV-cache VRAM scales)
- Prompt Cache Write & TTL Policy
- Automatic prefix KV-caching in vLLM / SGLang (0 cost)
- Computer Use & Browser GUI Agent
- Supported (Screen coordinate grounding, browser & desktop GUI action loops)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Built-in Google Search Grounding + Managed Python Code Execution Sandbox
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 19 GB VRAM (4-bit Quantized) · 67 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- Google DeepMind Frontier Safety Framework Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Gemma 4 31B Cost, Context, Hardware & API Integration
Open-weights or free-tier model: $0 API license cost when self-hosted.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Gemma 4 31B:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 68.5%
- GPQA Diamond
- 77%
- MMLU-Pro
- 84.8%
- HumanEval
- 92.5%
- AIME
- 86%
- Chatbot Arena Elo
- 1410pts
Strengths
- de frontera-grade razonamiento en un abierto-weight 31B package
- Expansive 262K ventana de contexto
- competitivo codificación y matemáticas benchmark scores
Limitations & Trade-offs
- requiere 32GB+ VRAM o 4-bit quantisation un run locally
- Slower generación velocidad cuando cadena de pensamiento es activo
Editorial Assessment
de Google insignia de pesos abiertos modelo de razonamiento de 2026.
Best for: privado empresarial razonamiento servers, local software development, y profundo investigación
Compare Gemma 4 31B
Frequently Asked Questions about Gemma 4 31B
How much does the Gemma 4 31B API cost per 1M tokens?+
Gemma 4 31B by Google is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Gemma 4 31B pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Gemma 4 31B's context window?+
Gemma 4 31B features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.
Can I run Gemma 4 31B locally on my own GPU (Open Weights)?+
Yes, Gemma 4 31B (31B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does Google train on data sent to the Gemma 4 31B API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does Gemma 4 31B perform on coding and reasoning benchmarks?+
Gemma 4 31B achieves a composite Intelligence Index of 81/100, scoring 68.5% on SWE-bench Verified, 77% on GPQA Diamond, 84.8% on MMLU-Pro, and 1410 pts on Chatbot Arena Elo.
What is Gemma 4 31B best used for?+
Gemma 4 31B is best suited for: privado empresarial razonamiento servers, local software development, y profundo investigación. Assessment: de Google insignia de pesos abiertos modelo de razonamiento de 2026.
Google Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Google's flagship reasoning tier:
Gemini 4 Argon
Gemini 3.8 Flash
Gemini 3.7 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash-Lite
Gemini Omni Flash
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Gemma 4 31B:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
Un modelo de IA entrenado para invertir cómputo adicional en pensar y validar hipótesis lógicas antes de responder, diseñado para problemas complejos de ingeniería y matemáticas.
Una técnica de razonamiento paso a paso donde el modelo genera pensamientos intermedios antes de formular la respuesta final, mejorando radicalmente la resolución de problemas matemáticos y lógicos.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.