UNPUBLISHED MODEL CATALOG
Ready for one-click deployment. InferX supports 200+ open models. This page lists configurations that can be deployed as dedicated endpoints from the InferX console.
Model / best use Context Pricing Access Action
READY NOW Popular production endpoints available immediately with pay-per-token access.
12 Independent Independent · Agents Agents A1 Long context Multi-GPU Context 262,000
Input / Output $0.12 / $0.90
Ready nowPay per token
Mistral AI · Devstral Devstral 2 123B Coding Multi-GPU Context 128,000
Input / Output $0.35 / $1.80
Ready nowPay per token
Ornith Ornith · Ornith Ornith 1.0 35B Long context Context 262,000
Input / Output $0.14 / $1.00
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3 Coder Next Coding Long context Multi-GPU Context 256,144
Input / Output $0.18 / $0.90
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3 Coder Next — No Thinking Coding Reasoning Long context Context 260,000
Input / Output $0.15 / $0.75
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3 Embedding 8B Dedicated Context —
Input / Output $0.01 / $0.00
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3.6 27B Coding Long context Context 262,144
Input / Output $0.25 / $2.80
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3.6 35B A3B Reasoning Long context MoE Context 262,000
Input / Output $0.12 / $0.90
Ready nowPay per token
Alibaba Cloud · Qwen Qwen3.6 35B A3B — No Thinking Reasoning Long context Context 262,000
Input / Output $0.10 / $0.75
Ready nowPay per token
Xiaomi Xiaomi · Mimo Mimo v2.5 Long context Context 1,000,000
Input / Output $0.09 / $0.19
Ready nowPay per token
Tencent · Hunyuan Hy3 Dedicated Context —
Input / Output $0.14 / $0.58
Ready nowPay per token
DeepSeek · DeepSeek DeepSeek V4 Flash Long context Context 1,000,000
Input / Output $0.09 / $0.19
Ready nowPay per token
Pricing and capability fields are shown only when published by the InferX catalog. Beta pricing currently reflects 50% off DeepSeek V4 and 40% off Mimo v2.5. Missing values are intentionally not estimated.