小波 API

Provides API access to AI models including GPT, Claude, and Gemini through a custom endpoint.

小波 API offers 269 LLM API models.

API pricing per token ranges from $0.685 to $164.38/M (input).

Speed benchmark average: 98 tok/s.

Avg Speed97.92 tok/s

Latency14.48 s

Updated4/18/2026

Created At8/13/2025

Recharge Rate¥10.00 per $1 quota

DrawingTaskData Export

Model Pricing

Pricing for 269 models (group: default, updated: 6/4/2026)

Model	Input ($/M)	Output ($/M)
[乾坤]grok-420-0.5Fixed	$0.685	$0.685
gemini-2.5-flashFixed	$0.685	$0.685
[低价]gemini-3-flash-preview-0.5Fixed	$0.685	$0.685
[低价]gemini-2.5-flashFixed	$0.685	$0.685
z-image-688x1216Fixed	$0.685	$0.685
z-image-1216x688Fixed	$0.685	$0.685
[低价]gemini-2.5-pro-不开流式Fixed	$0.685	$0.685
[bo]grok-4Fixed	$0.685	$0.685
z-image-832x1216Fixed	$0.685	$0.685
z-image-1216x832Fixed	$0.685	$0.685
[乾坤]gpt-5.5-0.5Fixed	$0.685	$0.685
z-image-1024x1024Fixed	$0.685	$0.685
z-image-turboFixed	$0.685	$0.685
[低价]gemini-3.1-pro-preview-0.5Fixed	$0.685	$0.685
[低价]gemini-3.5-flash-0.5Fixed	$0.685	$0.685
[乾坤]deepseek-v4-flash-0.5Fixed	$0.685	$0.685
grok-3Fixed	$0.822-79%	$0.822-96%
grok-4Fixed	$0.822	$0.822
[bo]grok-3Fixed	$0.822	$0.822
gemini-3-flash-preview-maxthinking-searchFixed	$1.37	$1.37

Showing 20 of 269 models.