Model Catalog
54 items
MiniMaxAI /
MiniMax-M2.1
8
Deployed 8 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
mistralai /
Devstral-Small-2-24B-Instruct-2512
17
Deployed 17 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia H200
$ 5
ibm-granite /
granite-3.3-8b-instruct-FP8
20
Deployed 20 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
openai /
gpt-oss-safeguard-20b
32
Deployed 32 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
allenai /
olmOCR-2-7B-1025-FP8
51
Deployed 51 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
Qwen /
Qwen3-VL-30B-A3B-Thinking
39
Deployed 39 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
Qwen /
Qwen3-VL-8B-Instruct
111
Deployed 111 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
lightonai /
LightOnOCR-1B-1025
39
Deployed 39 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
deepseek-ai /
DeepSeek-OCR
183
Deployed 183 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
zai-org /
GLM-4.1V-9B-Thinking
3
Deployed 3 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
ServiceNow-AI /
Apriel-1.5-15b-Thinker
4
Deployed 4 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
rednote-hilab /
dots.ocr
59
Deployed 59 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
nanonets /
Nanonets-OCR-s
22
Deployed 22 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
ibm-granite /
granite-4.0-micro
50
Deployed 50 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen3-Next-80B-A3B-Instruct
36
Deployed 36 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
Qwen /
Qwen3-Next-80B-A3B-Thinking
13
Deployed 13 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
openai /
gpt-oss-120b
278
Deployed 278 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia H200
$ 10
openai /
gpt-oss-20b
414
Deployed 414 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia H200
$ 5
Qwen /
Qwen3-32B
91
Deployed 91 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
ibm-granite /
granite-3.3-8b-instruct
26
Deployed 26 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
HuggingFaceTB /
SmolLM3-3B
42
Deployed 42 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen3-1.7B
117
Deployed 117 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen2.5-VL-7B-Instruct
241
Deployed 241 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
google /
paligemma2-10b-mix-448
2
Deployed 2 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
google /
paligemma2-10b-mix-224
3
Deployed 3 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
google /
paligemma2-3b-mix-448
19
Deployed 19 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
google /
gemma-3-12b-it
222
Deployed 222 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
google /
gemma-3-27b-it
275
Deployed 275 times
Image-Text-to-Text
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
microsoft /
phi-4
83
Deployed 83 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
meta-llama /
Meta-Llama-3-70B-Instruct
12
Deployed 12 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
microsoft /
Phi-3-mini-4k-instruct
67
Deployed 67 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
mistralai /
Mistral-Nemo-Instruct-2407
37
Deployed 37 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia L4
$ 3.8
meta-llama /
Llama-3.1-70B-Instruct
94
Deployed 94 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
mistralai /
Mistral-7B-Instruct-v0.3
403
Deployed 403 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen2.5-72B-Instruct
46
Deployed 46 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
mistralai /
Mixtral-8x22B-Instruct-v0.1
19
Deployed 19 times
Text Generation
vLLM
Accelerated vLLM
GPU 8x Nvidia A100
$ 20
openchat /
openchat-3.5-0106
31
Deployed 31 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
HuggingFaceH4 /
zephyr-7b-beta
59
Deployed 59 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen2.5-Coder-32B-Instruct
119
Deployed 119 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
microsoft /
Phi-3-mini-128k-instruct
84
Deployed 84 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
meta-llama /
Meta-Llama-3-8B-Instruct
95
Deployed 95 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
Qwen /
Qwen2.5-Coder-7B-Instruct
69
Deployed 69 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
deepseek-ai /
DeepSeek-R1-Distill-Llama-70B
119
Deployed 119 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia A100
$ 10
meta-llama /
Llama-3.1-8B-Instruct
479
Deployed 479 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia A100
$ 2.5
mistralai /
Mistral-Small-24B-Instruct-2501
55
Deployed 55 times
Text Generation
vLLM
Accelerated vLLM
GPU 4x Nvidia L4
$ 3.8
HuggingFaceTB /
SmolLM2-1.7B-Instruct
53
Deployed 53 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
Qwen /
Qwen2.5-14B-Instruct
158
Deployed 158 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
Qwen /
Qwen2.5-7B-Instruct
273
Deployed 273 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
Qwen /
QwQ-32B
62
Deployed 62 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
mistralai /
Mixtral-8x7B-Instruct-v0.1
138
Deployed 138 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
deepseek-ai /
DeepSeek-R1-Distill-Qwen-32B
140
Deployed 140 times
Text Generation
vLLM
Accelerated vLLM
GPU 2x Nvidia A100
$ 5
Qwen /
Qwen2.5-Coder-14B-Instruct
31
Deployed 31 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8
meta-llama /
Llama-3.2-1B-Instruct
58
Deployed 58 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L4
$ 0.8
meta-llama /
Llama-3.2-3B-Instruct
132
Deployed 132 times
Text Generation
vLLM
Accelerated vLLM
GPU 1x Nvidia L40S
$ 1.8