星见雅 API

A large model interface gateway providing proxy access to multiple AI models with free tiers and token incentives.

Categories

星见雅 API offers 314 LLM API models.

API pricing per token ranges from $0.100 to $7.50/M (input).

Speed benchmark average: 70 tok/s.

星见雅 API is an API aggregator, offering models from multiple vendors.

Avg Speed69.51 tok/s

Latency6.12 s

Total Tests426

Models54

Updated4/16/2026

Created At12/21/2025

Claim this provider

小Verified by 小保底必歪

Model Pricing

Pricing for 259 models (group: default, updated: 4/17/2026)

Model	Input ($/M)	Output ($/M)	Model Ratio	Completion Ratio
李/google/gemma-3-12b-it	Free	Free	0	1
李/google/gemma-3n-e2b-it	Free	Free	0	1
李/google/gemma-4-31b-it	Free	Free	0	1
李/google/gemma-3-27b-it	Free	Free	0	1
李/google/gemma-3n-e4b-it	Free	Free	0	1
李/speakleash/bielik-11b-v2.6-instruct	$0.100	$0.100	0.5	1
李/z-ai/glm5	$0.100	$0.100	0.5	1
英伟达/nvidia/llama-3.3-nemotron-super-49b-v1	$0.100	$0.100	0.5	1
李/deepseek-ai/deepseek-v3.1-terminus	$0.100	$0.100	0.5	1
英伟达/minimaxai/minimax-m2.7	$0.100	$0.100	0.5	1
英伟达/nvidia/llama-3.2-nemoretriever-300m-embed-v1	$0.100	$0.100	0.5	1
英伟达/nvidia/nemotron-mini-4b-instruct	$0.100	$0.100	0.5	1
英伟达/google/gemma-2-27b-it	$0.100	$0.100	0.5	1
英伟达/nvidia/nemotron-content-safety-reasoning-4b	$0.100	$0.100	0.5	1
英伟达/microsoft/phi-3-medium-128k-instruct	$0.100	$0.100	0.5	1
deepseek-chat	$0.100	$0.100	0.5	1
李/meta/llama-3.2-11b-vision-instruct	$0.100	$0.100	0.5	1
英伟达/nvidia/vila	$0.100	$0.100	0.5	1
英伟达/mistralai/mistral-large-2-instruct	$0.100	$0.100	0.5	1
英伟达/microsoft/phi-3.5-moe-instruct	$0.100	$0.100	0.5	1

Showing 20 of 259 models.