Gemma 4 31B — Specifications
Compilado por Mustafa Ihsan da documentação publicada pelo fornecedor · Última atualização
| Desenvolvedor | |
|---|---|
| Tipo | LLM (multimodal) |
| Modalidade | Texto, Imagem → Texto |
| Parâmetros | 30,7B |
| Janela de contexto | 256K |
| Licença | Apache 2.0 |
| Pesos abertos | Sim |
| Lançado | 2026-03 |
| Preço da entrada | $0.20 /1M |
| Preço da saída | $0.40 /1M |
| Provedores de API | DeepInfra, OpenRouter (hosted); Gemini API (free tier only); Ollama (local) |
Execute-o localmente
| VRAM (4 bits) | ~17.5 GB |
|---|
Benchmarks
| Google-reported | MMLU Pro 85.2%; GPQA Diamond 84.3%; LiveCodeBench v6 80.0%; AIME 2026 (no tools) 89.2%; MMMU Pro 76.9%. |
|---|
What is Gemma 4 31B?
Gemma 4 31B is the largest dense model in Google DeepMind’s open Gemma 4 family, released on 31 March 2026 under the Apache 2.0 licence. Its model card lists 30.7 billion parameters, text and image input, a 256K-token context window, configurable thinking modes and support for over 140 languages. Google reports 85.2% on MMLU Pro, 84.3% on GPQA Diamond and 80.0% on LiveCodeBench v6, against 67.6%, 42.4% and 29.1% for Gemma 3 27B without thinking.
Google estimates about 17.5 GB of memory to load it at 4-bit (Q4_0). That covers the weights only: the context window (KV cache) and supporting software need more on top. Ollama’s gemma4:31b-it-q4_K_M build is a 20 GB download, which will not fit in a 16 GB card’s memory but fits a 24 GB GPU with some room for context. Check a setup with the calculadora de VRAM e nosso guia para running Gemma 4 in Ollama.
Google’s Gemini API serves gemma-4-31b-it on its free tier only, with no paid tier. Hosted, DeepInfra charges $0.20 per million input tokens and $0.40 output, the price stored in this entry. It succeeds Gemma 3 27B. If speed matters more than peak quality, the mixture-of-experts Gemma 4 26B A4B needs less memory and, according to Google, runs almost as fast as a 4B model.
Gemma 4 31B pricing: API cost per 1M tokens
| Entrada (por 1 milhão de tokens) | $0.200 |
|---|---|
| Saída (por 1 milhão de tokens) | $0.400 |
| Razão saída/entrada | 2× |
| Misturada (4:1 entrada:saída) | $0.240 por 1 milhão de tokens |
What Gemma 4 31B costs per month
Gasto mensal real com uma proporção de entrada para saída de 4:1 — a razão efetivamente gerada por cargas de trabalho típicas de chat ou RAG.
| Carga de trabalho | Tokens/mês | Custo por mês |
|---|---|---|
| Projeto paralelo | 1 milhão de tokens de entrada / 0,25 milhão de tokens de saída | $0.30 |
| Equipe pequena | 20 milhões de tokens de entrada / 5 milhões de tokens de saída | $6.00 |
| Produção | 200 milhões de tokens de entrada / 50 milhões de tokens de saída | $60 |
Calcule seus próprios números na Calculadora de custos de API de IA.
Cheaper alternatives to Gemma 4 31B
| Modelo | Custo médio ponderado por US$ 1 milhão | Você economiza |
|---|---|---|
| Llama 3.1 8B aberta | $0.0240 | 90% cheaper |
| Mistral NeMo 12B aberta | $0.0292 | 88% mais barato |
| Gemma 3 4B aberta | $0.0600 | 75% mais barato |
Hospedar localmente ou pagar pela API?
Gemma 4 31B is open-weight, so you can run it yourself. It needs ~17.5 GB of VRAM at 4-bit. Self-hosting only beats the API once your volume is high enough to keep that hardware busy — the calculadora de self-hosting vs API calcula o ponto de equilíbrio para seu volume de tokens.
Perguntas frequentes
How much does Gemma 4 31B cost per 1M tokens?
Gemma 4 31B costs $0.200 per 1M input tokens and $0.400 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.240 per 1M tokens.
How much does Gemma 4 31B cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $6.00 on Gemma 4 31B. A side project (1M in / 0.25M out) costs roughly $0.30.
What is a cheaper alternative to Gemma 4 31B?
Llama 3.1 8B is the strongest cheaper option in our database at $0.0240 per 1M blended — about 90% less than Gemma 4 31B. It is also open-weight, so self-hosting is an option.
Can I run Gemma 4 31B locally?
Yes. Gemma 4 31B is open-weight and needs about ~17.5 GB of VRAM at 4-bit quantisation.
Why does Gemma 4 31B charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. Gemma 4 31B charges 2× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Os preços correspondem às tarifas listadas oficialmente para a API principal do modelo e são revisados conforme os provedores os atualizam. Descontos por volume, processamento em lote ou entradas em cache não estão incluídos. Compare todos os modelos lado a lado na Banco de dados de modelos de IA ou o Ranking de LLMs.