SMLC666 API

Name: SMLC666 API
Rating: 2.2 (5 reviews)

SMLC666 API provides an OpenAI-compatible API relay service with unified access to various AI models.

SMLC666 API offers 130 LLM API models.

API pricing per token ranges from $0.017 to $75.00/M (input).

Speed benchmark average: 43 tok/s.

Avg Speed43.11 tok/s

Latency3.21 s

Total Tests5

Models1

Updated4/17/2026

Created At1/8/2026

Model Pricing

Pricing for 130 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
google/gemma-3-4b-it	$0.017	$0.068	0.008515	4.0017614
google/gemma-3n-e4b-it	$0.020	$0.040	0.01	2
google/gemma-3-12b-it	$0.030	$0.100	0.015	3.3333333
meta-llama/llama-3.2-3b-instruct	$0.031	$0.049	0.0153	1.6111112
openai/gpt-oss-20b	$0.040	$0.180	0.02	4.5
nvidia/nemotron-nano-9b-v2	$0.040	$0.160	0.02	4
arcee-ai/trinity-mini	$0.045	$0.150	0.0225	3.3333333
meta-llama/llama-3.3-70b-instruct	$0.050	$0.230	0.025	4.6
mistralai/mistral-7b-instruct	$0.054	$0.054	0.0272	1
qwen/qwen3-4b	$0.071	$0.273	0.03575	3.8181818
openai/gpt-oss-120b	$0.080	$0.440	0.04	5.5
llama3.1-8b	$0.100	$0.100	0.05	1
gemini-2.5-flash-lite	$0.100	$0.400	0.05	4
xiaomi/mimo-v2-flash	$0.102	$0.306	0.051	3
z-ai/glm-4.5-air	$0.110	$0.560	0.055	5.090909
mistralai/devstral-2512	$0.150	$0.600	0.075	4
nvidia/nemotron-3-nano-30b-a3b	$0.170	$0.680	0.085	4
qwen/qwen-2.5-vl-7b-instruct	$0.200	$0.200	0.1	1
nvidia/nemotron-nano-12b-v2-vl	$0.200	$0.600	0.1	3
minimax-m2	$0.200	$1.00	0.1	5

Showing 20 of 130 models.