Gemma 4 31B

Chat Completions API

gemma-4-31b-it

от

GoogleСоздана 12 апр. 2026 г.256K контекст

Chat Completions API

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model developed by Google DeepMind. While it has 25.2B parameters in total, only 3.8B are activated per token during inference — providing performance close to a 31B model at a much lower computational cost. It supports multimodal inputs such as text, images, and video (up to 60 seconds at 1 fps). Key features include a 256K-token context window, native function calling, an adjustable thinking/reasoning mode, and support for structured outputs. It is released under the Apache 2.0 license.

Сравнить Открыть в Плейграунде

Здесь собран публичный контракт интеграции модели: поддерживаемые API-методы, параметры запросов и примеры вызовов.

Chat Completions APIPOST/v1/chat/completions

curl https://api.makura.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  --data-raw '{
  "model": "gemma-4-31b-it",
  "messages": [
    {
      "role": "user",
      "content": "Сколько будет 2 + 2?"
    }
  ]
}'

Max Completion TokensReasoning EffortResponse FormatStopTemperatureTool ChoiceToolsTop PWeb Search Options

Gemma 4 31B

API-методы и структура запроса

Пример кода

Параметры