262K
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
全部模型获取 API 密钥
上下文
262K
- 输入
- 文本
- 输出
- 文本
- 提供方
- Google AI Studio
- 列表更新
- 2026年10月29日 20:28 UTC
Gemma 4 through Google AI Studio. Input and output are free under the current Gemini API pricing. Account rate and region limits apply. Free-tier content may be used to improve Google products. This gateway supports text and function tools; connect your own Google API key.
API
google/gemma-4-26b-a4b-itcurl https://staging.freemodel.io/api/v1/chat/completions \
-H "Authorization: Bearer $FREEMODEL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemma-4-26b-a4b-it",
"messages": [{"role": "user", "content": "Hello"}]
}'google 的更多模型
262K
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...