352287 API

352287 API provides an OpenAI-compatible API relay for accessing multiple AI models.

Categories

352287 API offers 44 LLM API models.

API pricing per token ranges from $0.010 to $75.00/M (input).

Speed benchmark average: 191 tok/s.

Avg Speed190.51 tok/s

Latency0.92 s

Total Tests19

Models4

Updated4/18/2026

Created At8/13/2025

Versionv0.12.14

Online SinceApr 17, 2026, 04:46 PM

DrawingTaskData Export

Passkey

Model Pricing

Pricing for 44 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
BAAI/bge-reranker-v2-m3	Free	Free	0	0
Qwen/Qwen3-Embedding-8B	Free	Free	0	0
Qwen3-8B	Free	Free	0	0
mvuFixed	$0.010	$0.010	0	0
openai/gpt-oss-20b	$0.030	$0.140	0.015	4.6666665
nvidia/nemotron-3-nano-30b-a3b	$0.060	$0.240	0.03	4
stepfun/step-3.5-flash	$0.100	$0.300	0.05	3
gemini-2.5-flash-lite	$0.100	$0.400	0.05	4
gemini-2.0-flash	$0.100	$0.400	0.05	4
qwen/qwen3-next-80b-a3b-instruct	$0.140	$1.40	0.07	10
gemini-embedding-001	$0.150	$0.150	0.075	1
Qwen/Qwen3-VL-32B-Instruct	$0.200	$0.600	0.1	3
deepseek-v3.1-terminus	$0.270	$1.00	0.135	3.7037036
glm-4.7	$0.270	$1.10	0.135	4.0740743
deepseek-v3.2	$0.280	$0.420	0.14	1.5
gemini-2.5-flash	$0.300	$2.50	0.15	8.333333
MiniMax-M2.5	$0.300	$1.20	0.15	4
MiniMax-M2	$0.300	$1.20	0.15	4
MiniMax-M2.1	$0.300	$1.20	0.15	4
qwen/qwen3-coder-480b-a35b-instruct	$0.400	$1.80	0.2	4.5

Showing 20 of 44 models.