The Index / NanoGPT / Gemma 4 31B Split-Untied Gemma 4 31B Split-Untied by NanoGPT · family gemma · listed Sep 2026T W
Blazed-Forge's Split-Untied is a text-only Gemma 4 31B community finetune with an untied BF16 output head, built for creative writing, roleplay, expressive dialogue, and tool use.
Current rates USD per 1M tokens Input $0.10
Output $0.30
Cache read $0.05
Cache write —
Against the market Input price vs. maker flagships ($/1M tokens) Gemma 4 31B Split-Untied Gemma 4 31B Split-Untied: $0.10 per 1M tokens $0.10 DeepSeek V4 Flash Vision Exp DeepSeek V4 Flash Vision Exp: $0.15 per 1M tokens $0.15 Qwen3.8 Omni Flash Qwen3.8 Omni Flash: $0.15 per 1M tokens $0.15 Gemini 3.8 Flash Gemini 3.8 Flash: $0.75 per 1M tokens $0.75 GLM-5.3 GLM-5.3: $1.40 per 1M tokens $1.40 Claude Sonnet 5.5 Claude Sonnet 5.5: $2.00 per 1M tokens $2.00 GPT-6.1 Sol GPT-6.1 Sol: $2.00 per 1M tokens $2.00 Grok 4.7 Grok 4.7: $2.00 per 1M tokens $2.00 Output price vs. maker flagships ($/1M tokens) Gemma 4 31B Split-Untied Gemma 4 31B Split-Untied: $0.30 per 1M tokens $0.30 Qwen3.8 Omni Flash Qwen3.8 Omni Flash: $0.47 per 1M tokens $0.47 DeepSeek V4 Flash Vision Exp DeepSeek V4 Flash Vision Exp: $0.60 per 1M tokens $0.60 Gemini 3.8 Flash Gemini 3.8 Flash: $3.75 per 1M tokens $3.75 GLM-5.3 GLM-5.3: $4.40 per 1M tokens $4.40 Grok 4.7 Grok 4.7: $6.00 per 1M tokens $6.00 Claude Sonnet 5.5 Claude Sonnet 5.5: $10.00 per 1M tokens $10.00 GPT-6.1 Sol GPT-6.1 Sol: $10.00 per 1M tokens $10.00 On the record
Model id google/gemma4-31b-splituntied
Context window 262K tokens
Max output 33K tokens
Input modalities text
Output modalities text
Reasoning no
Tool calls yes
Open weights yes
Knowledge cutoff —
Released 2026-09-17
Last updated 2026-09-17 ← All NanoGPT listings