The Index / NanoGPT / Gemma 4 12B Instruct Gemma 4 12B Instruct by NanoGPT · family gemma · listed Aug 2026T V W
Google's Gemma 4 12B Instruct is an open-weight multimodal model for text, image, audio, and video understanding, with tool calling and structured output support.
Current rates USD per 1M tokens Input $0.06
Output $0.30
Cache read $0.03
Cache write —
Against the market Input price vs. maker flagships ($/1M tokens) Gemma 4 12B Instruct Gemma 4 12B Instruct: $0.06 per 1M tokens $0.06 DeepSeek V4 Pro DeepSeek V4 Pro: $0.435 per 1M tokens $0.435 Gemini 3.7 Flash Gemini 3.7 Flash: $0.75 per 1M tokens $0.75 Mistral Medium 3.5 Mistral Medium 3.5: $1.50 per 1M tokens $1.50 Grok 4.6 Grok 4.6: $2.00 per 1M tokens $2.00 Qwen3.8 Max Qwen3.8 Max: $2.00 per 1M tokens $2.00 Claude Opus 5 Claude Opus 5: $5.00 per 1M tokens $5.00 GPT-5.6 Sol GPT-5.6 Sol: $5.00 per 1M tokens $5.00 Output price vs. maker flagships ($/1M tokens) Gemma 4 12B Instruct Gemma 4 12B Instruct: $0.30 per 1M tokens $0.30 DeepSeek V4 Pro DeepSeek V4 Pro: $0.87 per 1M tokens $0.87 Gemini 3.7 Flash Gemini 3.7 Flash: $3.75 per 1M tokens $3.75 Grok 4.6 Grok 4.6: $6.00 per 1M tokens $6.00 Qwen3.8 Max Qwen3.8 Max: $6.00 per 1M tokens $6.00 Mistral Medium 3.5 Mistral Medium 3.5: $7.50 per 1M tokens $7.50 Claude Opus 5 Claude Opus 5: $25.00 per 1M tokens $25.00 GPT-5.6 Sol GPT-5.6 Sol: $30.00 per 1M tokens $30.00 On the record
Model id gemma-4-12b-it
Context window 262K tokens
Max output 33K tokens
Input modalities text, image, video, audio
Output modalities text
Reasoning no
Tool calls yes
Open weights yes
Knowledge cutoff —
Released 2026-08-01
Last updated 2026-08-01 ← All NanoGPT listings