ai.api.xn--fiqs8s

Provides unified API access to over 300 AI models from multiple providers, including OpenAI, Claude, and Gemini.

Categories

ai.api.xn--fiqs8s offers 22 LLM API models.

API pricing per token ranges from $0.030 to $13.50/M (input).

Speed benchmark average: 115 tok/s.

ai.api.xn--fiqs8s is an API aggregator, offering models from multiple vendors.

Avg Speed114.52 tok/s

Latency2.81 s

Total Tests175

Models22

Updated4/18/2026

Created At8/13/2025

Versionv1.0.0-hotfix2

Online SinceApr 17, 2026, 11:11 AM

DrawingTaskData ExportCheck-in

Supported Models

Model	Speed	Latency	Tests
gemini-1.5-flash-8b	275.08 tok/s	1.28s	10
gemini-2.0-flash-thinking-exp-01-21	230.82 tok/s	7.47s	5
gemini-2.0-flash-lite-preview-02-05	188.38 tok/s	1.06s	15
gemini-2.0-flash	177.30 tok/s	0.98s	20
gemini-1.5-flash-latest	159.78 tok/s	1.26s	10
gemini-1.5-flash	158.26 tok/s	0.91s	5
gemini-1.5-flash-002	155.08 tok/s	1.62s	5
gpt-4o	135.41 tok/s	1.43s	5
gemini-2.0-flash-exp	125.02 tok/s	1.40s	5
qwen-72b	102.22 tok/s	3.11s	5
qwen2.5-72b-instruct	92.64 tok/s	2.57s	10
gpt-4o-mini	78.22 tok/s	1.05s	5
o3-mini-all	74.59 tok/s	5.09s	10
BLOOMZ-7B	70.56 tok/s	2.46s	5
o3-mini	60.31 tok/s	7.42s	15
Phi-4	43.07 tok/s	1.32s	10
claude-3-5-sonnet-20241022	39.36 tok/s	4.75s	5
qwen2.5-7b-instruct	34.15 tok/s	1.01s	5
deepseek-reasoner	29.86 tok/s	4.71s	5
deepseek-v3	26.71 tok/s	3.41s	5

Showing 20 of 22 models.