SanShui API

Provides access to multiple AI models including GPT, Claude, DeepSeek, and Grok through a unified API interface.

Categories

SanShui API offers 719 LLM API models.

API pricing per token ranges from $0.010 to $350.00/M (input).

Speed benchmark average: 7 tok/s.

Avg Speed6.52 tok/s

Latency3.52 s

Total Tests10

Models2

Updated4/18/2026

Created At8/13/2025

Versionv0.10.9-alpha.3

Online SinceFeb 9, 2026, 11:56 AM

DrawingTaskData Export

Model Pricing

Pricing for 719 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
mj_modal	Free	Free	0	0
grok-3-reasonerFixed	$0.010	$0.010	0	0
gemini-veoFixed	$0.010	$0.010	0	0
grok-3-deepsearchFixed	$0.010	$0.010	0	0
stable-diffusion-3-2bFixed	$0.010	$0.010	0	0
playground-v2.5Fixed	$0.010	$0.010	0	0
text-embedding-3-small	$0.020	$0.020	0.01	1
ideogramFixed	$0.030	$0.030	0	0
glm-4-flash	$0.030	$0.030	0.015	1
gemini-1.5-flash-8b	$0.037	$0.150	0.01875	4
gpt-4o-imageFixed	$0.060	$0.060	0	0
gemini-1.5-flash	$0.075	$0.300	0.0375	4
gemini-2.5-flash	$0.075	$0.300	0.0375	4
text-embedding-v1	$0.100	$0.100	0.05	1
mistral-embed	$0.100	$0.300	0.05	3
mj_upscaleFixed	$0.100	$0.100	0	0
gemini-imagenFixed	$0.100	$0.100	0	0
text-embedding-ada-002	$0.100	$0.100	0.05	1
vidu-videoFixed	$0.100	$0.100	0	0
mj_describeFixed	$0.100	$0.100	0	0

Showing 20 of 719 models.