A unified LLM API gateway providing access to multiple AI models through a single endpoint with competitive pricing and no subscription required.

Qwen2 DeepSeek-VL DeepSeek-VL2 Qwen2-VL Qwen2.5 Qwen2.5-VL GLM-4 Qwen3 DeepSeek-V2 DeepSeek-V2.5 DeepSeek-V3

New API offers a unified gateway for accessing various large language models and AI services through standardized endpoints. The service supports models from providers including MoonshotAI, OpenAI, Grok, Zhipu, Volcengine, Cohere, Claude, Gemini, Suno, Minimax, Wenxin, Spark, Qingyan, DeepSeek, Qwen, Midjourney, AzureAI, Hunyuan, and Xinference.

Key endpoints include:

/v1/chat/completions for chat completions
/v1/embeddings for embedding generation
/v1/rerank for reranking functionality
/v1/images/generations, /v1/images/edits, and /v1/images/variations for image generation and manipulation
/v1/audio/speech, /v1/audio/transcriptions, and /v1/audio/translations for audio processing
/v1beta/models for model information

The platform emphasizes better pricing and stability compared to direct provider access, with no subscription requirements. Users can integrate by replacing their model BASE URL with the provided endpoints. Typical use cases include AI-powered applications requiring multiple model types, developers seeking simplified API management across providers, and projects needing cost-effective access to various AI capabilities.

A unified LLM API gateway providing access to multiple AI models through a single endpoint with competitive pricing and no subscription required.

Qwen2 DeepSeek-VL DeepSeek-VL2 Qwen2-VL Qwen2.5 Qwen2.5-VL GLM-4 Qwen3 DeepSeek-V2 DeepSeek-V2.5 DeepSeek-V3

Key endpoints include:

/v1/chat/completions for chat completions
/v1/embeddings for embedding generation
/v1/rerank for reranking functionality
/v1/images/generations, /v1/images/edits, and /v1/images/variations for image generation and manipulation
/v1/audio/speech, /v1/audio/transcriptions, and /v1/audio/translations for audio processing
/v1beta/models for model information

Model	Speed	Latency	Tests
Qwen/Qwen2-1.5B-Instruct	213.84 t/s	0.67s	5
Pro/Qwen/Qwen2-1.5B-Instruct	204.04 t/s	0.60s	5
免费Qwen2-1.5B	203.36 t/s	0.68s	5
免费Grok3-mini	180.93 t/s	3.99s	5
deepseek-ai/deepseek-vl2	125.77 t/s	0.75s	5
deepseek-ai/deepseek-vl2	125.77 t/s	0.75s	5
Pro/Qwen/Qwen2-7B-Instruct	96.25 t/s	0.63s	5
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	94.25 t/s	5.51s	5
Qwen/Qwen2-7B-Instruct	93.64 t/s	0.68s	5
Pro/Qwen/Qwen2-VL-7B-Instruct	93.23 t/s	0.71s	5
Pro/Qwen/Qwen2-VL-7B-Instruct	93.23 t/s	0.71s	5
免费Qwen2-7B	93.01 t/s	0.85s	10
免费DS-VL2	86.80 t/s	1.86s	5
免费Grok3	85.51 t/s	1.39s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
免费Qwen2.5-14B	77.95 t/s	0.69s	5
免费Qwen2.5-14B	77.95 t/s	0.69s	5
Qwen/Qwen2.5-14B-Instruct	77.92 t/s	0.69s	5
Qwen/Qwen2.5-14B-Instruct	77.92 t/s	0.69s	5
免费Qwen2-VL-7B	77.82 t/s	0.95s	10
免费Qwen2-VL-7B	77.82 t/s	0.95s	10
internlm/internlm2_5-7b-chat	73.88 t/s	0.61s	5
免费GLM-4-9B-128K	73.70 t/s	0.77s	5
Qwen/QwQ-32B-Preview	72.57 t/s	0.81s	5
THUDM/glm-4-9b-chat	71.17 t/s	0.65s	5
Qwen/QwQ-32B	69.22 t/s	14.67s	5
Qwen/Qwen3-30B-A3B	69.20 t/s	13.40s	15
Pro/THUDM/glm-4-9b-chat	68.04 t/s	0.87s	5
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
internlm/internlm2_5-20b-chat	61.81 t/s	0.77s	5
Qwen/Qwen2.5-32B-Instruct	60.92 t/s	0.86s	5
Qwen/Qwen2.5-32B-Instruct	60.92 t/s	0.86s	5
火山R1-32B	48.09 t/s	22.59s	5
火山V3	38.75 t/s	1.26s	5
Qwen/Qwen2.5-72B-Instruct	34.81 t/s	0.74s	5
Qwen/Qwen2.5-72B-Instruct	34.81 t/s	0.74s	5
THUDM/chatglm3-6b	32.18 t/s	0.74s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/QVQ-72B-Preview	28.92 t/s	1.01s	5
Qwen/Qwen2-VL-72B-Instruct	28.50 t/s	0.78s	5
Qwen/Qwen2-VL-72B-Instruct	28.50 t/s	0.78s	5
硅基-付费-Pro-R1	25.53 t/s	29.06s	5
免费V3-0324	24.37 t/s	1.60s	5
free:QwQ-32B	23.47 t/s	21.01s	5
Qwen/Qwen2.5-72B-Instruct-128K	22.28 t/s	0.94s	5
Qwen/Qwen2.5-72B-Instruct-128K	22.28 t/s	0.94s	5
官方R1	21.84 t/s	53.05s	15
硅基-R1	21.39 t/s	41.74s	5
Pro/Qwen/Qwen2.5-7B-Instruct	20.74 t/s	0.87s	5
Pro/Qwen/Qwen2.5-7B-Instruct	20.74 t/s	0.87s	5
Qwen/Qwen2.5-7B-Instruct	20.51 t/s	0.79s	5
Qwen/Qwen2.5-7B-Instruct	20.51 t/s	0.79s	5
火山R1	20.37 t/s	13.34s	25
deepseek-ai/DeepSeek-V2.5	16.01 t/s	1.14s	5
deepseek-ai/DeepSeek-V2.5	16.01 t/s	1.14s	5
沉浸式翻译	14.45 t/s	0.20s	25
deepseek-ai/DeepSeek-V3	11.66 t/s	1.75s	5
gpt-4.1-mini	0.00 t/s	0.00s	5

Time	Model	Speed	Latency
Jun 19, 03:51 PM	gpt-4.1-mini	0.00 t/s	0.00s
Jun 19, 03:50 PM	沉浸式翻译	0.00 t/s	0.00s
Jun 19, 03:49 PM	沉浸式翻译	0.00 t/s	0.00s
Jun 11, 06:54 AM	沉浸式翻译	0.00 t/s	0.00s
Jun 11, 06:54 AM	沉浸式翻译	0.00 t/s	0.00s
Jun 8, 11:16 PM	沉浸式翻译	72.24 t/s	1.01s
May 3, 03:43 PM	Qwen/Qwen3-30B-A3B	63.72 t/s	19.32s
May 3, 03:41 PM	Qwen/Qwen3-30B-A3B	84.79 t/s	9.54s
May 3, 11:26 AM	Qwen/Qwen3-30B-A3B	59.10 t/s	11.34s
Apr 19, 06:13 PM	免费V3-0324	24.37 t/s	1.60s

Model	Speed	Latency	Tests
Qwen/Qwen2-1.5B-Instruct	213.84 t/s	0.67s	5
Pro/Qwen/Qwen2-1.5B-Instruct	204.04 t/s	0.60s	5
免费Qwen2-1.5B	203.36 t/s	0.68s	5
免费Grok3-mini	180.93 t/s	3.99s	5
deepseek-ai/deepseek-vl2	125.77 t/s	0.75s	5
deepseek-ai/deepseek-vl2	125.77 t/s	0.75s	5
Pro/Qwen/Qwen2-7B-Instruct	96.25 t/s	0.63s	5
deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B	94.25 t/s	5.51s	5
Qwen/Qwen2-7B-Instruct	93.64 t/s	0.68s	5
Pro/Qwen/Qwen2-VL-7B-Instruct	93.23 t/s	0.71s	5
Pro/Qwen/Qwen2-VL-7B-Instruct	93.23 t/s	0.71s	5
免费Qwen2-7B	93.01 t/s	0.85s	10
免费DS-VL2	86.80 t/s	1.86s	5
免费Grok3	85.51 t/s	1.39s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
Pro/Qwen/Qwen2.5-VL-7B-Instruct	85.51 t/s	0.76s	5
免费Qwen2.5-14B	77.95 t/s	0.69s	5
免费Qwen2.5-14B	77.95 t/s	0.69s	5
Qwen/Qwen2.5-14B-Instruct	77.92 t/s	0.69s	5
Qwen/Qwen2.5-14B-Instruct	77.92 t/s	0.69s	5
免费Qwen2-VL-7B	77.82 t/s	0.95s	10
免费Qwen2-VL-7B	77.82 t/s	0.95s	10
internlm/internlm2_5-7b-chat	73.88 t/s	0.61s	5
免费GLM-4-9B-128K	73.70 t/s	0.77s	5
Qwen/QwQ-32B-Preview	72.57 t/s	0.81s	5
THUDM/glm-4-9b-chat	71.17 t/s	0.65s	5
Qwen/QwQ-32B	69.22 t/s	14.67s	5
Qwen/Qwen3-30B-A3B	69.20 t/s	13.40s	15
Pro/THUDM/glm-4-9b-chat	68.04 t/s	0.87s	5
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
免费Qwen2.5-VL-7B	63.63 t/s	1.03s	10
internlm/internlm2_5-20b-chat	61.81 t/s	0.77s	5
Qwen/Qwen2.5-32B-Instruct	60.92 t/s	0.86s	5
Qwen/Qwen2.5-32B-Instruct	60.92 t/s	0.86s	5
火山R1-32B	48.09 t/s	22.59s	5
火山V3	38.75 t/s	1.26s	5
Qwen/Qwen2.5-72B-Instruct	34.81 t/s	0.74s	5
Qwen/Qwen2.5-72B-Instruct	34.81 t/s	0.74s	5
THUDM/chatglm3-6b	32.18 t/s	0.74s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-32B-Instruct	30.07 t/s	0.87s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/Qwen2.5-VL-72B-Instruct	29.83 t/s	0.98s	5
Qwen/QVQ-72B-Preview	28.92 t/s	1.01s	5
Qwen/Qwen2-VL-72B-Instruct	28.50 t/s	0.78s	5
Qwen/Qwen2-VL-72B-Instruct	28.50 t/s	0.78s	5
硅基-付费-Pro-R1	25.53 t/s	29.06s	5
免费V3-0324	24.37 t/s	1.60s	5
free:QwQ-32B	23.47 t/s	21.01s	5
Qwen/Qwen2.5-72B-Instruct-128K	22.28 t/s	0.94s	5
Qwen/Qwen2.5-72B-Instruct-128K	22.28 t/s	0.94s	5
官方R1	21.84 t/s	53.05s	15
硅基-R1	21.39 t/s	41.74s	5
Pro/Qwen/Qwen2.5-7B-Instruct	20.74 t/s	0.87s	5
Pro/Qwen/Qwen2.5-7B-Instruct	20.74 t/s	0.87s	5
Qwen/Qwen2.5-7B-Instruct	20.51 t/s	0.79s	5
Qwen/Qwen2.5-7B-Instruct	20.51 t/s	0.79s	5
火山R1	20.37 t/s	13.34s	25
deepseek-ai/DeepSeek-V2.5	16.01 t/s	1.14s	5
deepseek-ai/DeepSeek-V2.5	16.01 t/s	1.14s	5
沉浸式翻译	14.45 t/s	0.20s	25
deepseek-ai/DeepSeek-V3	11.66 t/s	1.75s	5
gpt-4.1-mini	0.00 t/s	0.00s	5

Time	Model	Speed	Latency
Jun 19, 03:51 PM	gpt-4.1-mini	0.00 t/s	0.00s
Jun 19, 03:50 PM	沉浸式翻译	0.00 t/s	0.00s
Jun 19, 03:49 PM	沉浸式翻译	0.00 t/s	0.00s
Jun 11, 06:54 AM	沉浸式翻译	0.00 t/s	0.00s
Jun 11, 06:54 AM	沉浸式翻译	0.00 t/s	0.00s
Jun 8, 11:16 PM	沉浸式翻译	72.24 t/s	1.01s
May 3, 03:43 PM	Qwen/Qwen3-30B-A3B	63.72 t/s	19.32s
May 3, 03:41 PM	Qwen/Qwen3-30B-A3B	84.79 t/s	9.54s
May 3, 11:26 AM	Qwen/Qwen3-30B-A3B	59.10 t/s	11.34s
Apr 19, 06:13 PM	免费V3-0324	24.37 t/s	1.60s

New API

Supported Models

Recent Test Records

New API

Supported Models

Recent Test Records

New API

About New API

Supported Models

Recent Test Records

New API

About New API

Supported Models

Recent Test Records