丸美小沐写作

A Windows desktop application for AI-assisted novel writing, supporting multiple AI models and batch generation.

丸美小沐写作 offers 18 LLM API models.

API pricing per token ranges from $0.486 to $75.00/M (input).

Speed benchmark average: 147 tok/s.

Avg Speed146.97 tok/s

Latency0.81 s

Updated4/18/2026

Created At8/13/2025

Recharge Rate¥1.00 per $1 quota

DrawingTaskData ExportCheck-in

Model Pricing

Pricing for 18 models (group: default, updated: 6/3/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
deepseek-chat	$0.486	$0.486	0.243	1
deepseek-reasoner	$0.990	$0.990	0.495	1
gemini-embedding-001	$1.00	$2.00	0.5	2
gemini-3.1-flash-preview	$1.20	$4.20	0.6	3.5
gpt-5.5	$1.60	$12.80	0.8	8
gpt-5.4	$1.60-36%	$12.80-15%	0.8	8
gemini-3-flash-preview	$1.62	$4.05	0.81	2.5
o3-mini	$1.98	$7.92	0.99	4
gpt-5.2	$2.40	$19.20	1.2	8
claude-haiku-4-5-20251001	$3.20	$16.00	1.6	5
gemini-3.1-pro-preview	$3.60	$19.80	1.8	5.5
gemini-3-pro-preview	$3.60	$19.80	1.8	5.5
deepseek-v4-pro	$4.00	$6.00	2	1.5
claude-sonnet-4-6	$8.28	$41.40	4.14	5
claude-opus-4-6	$13.50	$67.50	6.75	5
deepseek-v3	$75.00	$75.00	37.5	1
deepseek-v4-flash	$75.00	$75.00	37.5	1
deepseek-r1	$75.00	$75.00	37.5	1