> BROMANDER_LABS
DOES ITFIT IN 128K?
Paste your codebase, docs, or chat history. See exactly which models can hold it — and where the wall is. From 32K all the way to 10M tokens.
Everything stays in your browser. We never see your text.
01 — Your sources
0
0
Total
0
tokens
Estimate based on char-density per kind. Real tokenizer per model may differ ±20%.
02 — Where it fits
Fits in
29 / 29
Total input
0 tokens
Llama 4 Scout
10M0.00% full10.5M headroom
Gemini 2.5 Pro
2.1M0.00% full2.10M headroom
Kimi K3
1.0M0.00% full1.05M headroom
Gemini 3.7 Flash
1.0M0.00% full1.05M headroom
Gemini 3.1 Pro
1.0M0.00% full1.05M headroom
GLM-5.3
1.0M0.00% full1.05M headroom
MiniMax M3
1.0M0.00% full1.05M headroom
DeepSeek V4 Pro
1.0M0.00% full1.05M headroom
Llama 4 Maverick
1.0M0.00% full1.05M headroom
GPT-5.6 Sol
1.0M0.00% full1.05M headroom
GPT-4.1
1.0M0.00% full1.05M headroom
Claude Opus 5
1.0M0.00% full1.00M headroom
Claude Sonnet 5
1.0M0.00% full1.00M headroom
Qwen3.8-Max
1.0M0.00% full1.00M headroom
Grok 4.3
1.0M0.00% full1.00M headroom
Grok 4.6
500K0.00% full500K headroom
GPT-5.5
272K0.00% full272K headroom
Kimi K2.6
262K0.00% full262K headroom
Qwen3.8 27B
262K0.00% full262K headroom
Gemma 4 31B
262K0.00% full262K headroom
Claude Haiku 4.5
200K0.00% full200K headroom
GLM-4.7
200K0.00% full200K headroom
MiniMax M2.5
197K0.00% full197K headroom
Llama 3.1 / 3.3
131K0.00% full131K headroom
Mistral Large 3
131K0.00% full131K headroom
GLM-4.5-Air
131K0.00% full131K headroom
GPT-4o
128K0.00% full128K headroom
Qwen3 32B
33K0.00% full33K headroom
QwQ 32B
33K0.00% full33K headroom
─── Your Fit Report ───
The link encodes only your token count, never your text. Sharing produces this card on X, LinkedIn, and Facebook.
Live preview
Need help with RAG / long-context pipelines?
Talk to Bromander Studios