鲨鱼魔法

鲨鱼魔法 (sharkmagic.top) provides access to official paid AI models like Gemini, Claude, and GPT through a unified proxy with OpenAI-compatible API.

鲨鱼魔法 offers 712 LLM API models.

API pricing per token ranges from $0.050 to $9600.00/M (input).

Speed benchmark average: 108 tok/s.

Avg Speed108.16 tok/s

Latency16.16 s

Total Tests29

Models6

Updated4/18/2026

Created At1/11/2026

Model Pricing

Pricing for 712 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)
[su]q\|cb/autoFixed	$0.050	$0.050
[ba]q\|假流式/gemini-2.5-flash-nothinking-searchFixed	$2.00	$2.00
[hm]q\|cli/gemini-2.5-flashFixed	$2.00	$2.00
[su]q\|anti/gemini-3-flash-previewFixed	$2.00	$2.00
[ba]q\|假流式/gemini-2.5-flash-searchFixed	$2.00	$2.00
[ba]q\|流式抗截断/gemini-2.5-flash-maxthinking-searchFixed	$2.00	$2.00
[ba]q\|流式抗截断/gemini-2.5-flash-maxthinkingFixed	$2.00	$2.00
[ba]q\|gemini-2.5-flash-maxthinking-searchFixed	$2.00	$2.00
[hm]q\|cli/gemini-2.5-flash-maxthinkingFixed	$2.00	$2.00
[su]q\|cli/gemini-3-flash-previewFixed	$2.00	$2.00
[ba]q\|假流式/gemini-2.5-flashFixed	$2.00	$2.00
[su]q\|cli/gemini-2.5-flash-liteFixed	$2.00	$2.00
[ba]q\|gemini-2.5-flashFixed	$2.00	$2.00
[su]q\|cli/gemini-3.1-flash-lite-previewFixed	$2.00	$2.00
[ba]q\|流式抗截断/gemini-2.5-flashFixed	$2.00	$2.00
[hm]q\|cli/gemini-2.5-flash-nothinkingFixed	$2.00	$2.00
[hm]q\|cli/gemini-2.5-flash-maxthinking-searchFixed	$2.00	$2.00
[ba]q\|流式抗截断/gemini-2.5-flash-nothinking-searchFixed	$2.00	$2.00
[su]q\|anti/gemini-2.5-flashFixed	$2.00	$2.00
[su]q\|anti/gemini-2.5-flash-liteFixed	$2.00	$2.00

Showing 20 of 712 models.