Models
Popular AI models on nfer
The most popular open-weight and frontier models with a dedicated hosting-cost page — pick one to see API token pricing, dedicated capacity, and rented GPU costs ranked side-by-side.
DeepSeek-V3.2
685BDeepSeek · 8 providers
API from $0.26 /1M inGPU from $3.50/hr
Llama-3.1-8B-Instruct
8.0BMeta · 12 providers
API from $0.02 /1M inGPU from $0.28/hr
DeepSeek-R1
685BDeepSeek · 7 providers
API from $1.35 /1M inGPU from $3.50/hr
Mistral-7B-Instruct-v0.3
7.2BMistral AI · 10 providers
API from $0.11 /1M inGPU from $0.28/hr
Qwen3-Coder-30B-A3B-Instruct
31Bqwen · 9 providers
API from $0.07 /1M inGPU from $0.55/hr
gemma-3-4b-it
4.3BGoogle · 11 providers
API from $0.04 /1M inGPU from $0.14/hr
Meta-Llama-3-8B-Instruct
8.0BMeta · 11 providers
API from $0.03 /1M inGPU from $0.28/hr
MiniMax-M2.5
229Bminimaxai · 10 providers
API from $0.15 /1M inGPU from $1.24/hr
NVIDIA-Nemotron-3-Super-120B-A12B-BF16
124BNVIDIA · 7 providers
API from $0.15 /1M inGPU from $1.24/hr
Llama-3.3-70B-Instruct
71BMeta · 12 providers
API from $0.13 /1M inGPU from $1.13/hr
Llama-3.1-70B-Instruct
71BMeta · 10 providers
API from $0.40 /1M inGPU from $1.13/hr
Mixtral-8x7B-Instruct-v0.1
47BMistral AI · 11 providers
API from $0.54 /1M inGPU from $1.10/hr
MiniMax-M2.7
229Bminimaxai · 8 providers
API from $0.30 /1M inGPU from $1.24/hr
gemma-3-27b-it
27BGoogle · 10 providers
API from $0.08 /1M inGPU from $0.55/hr
Qwen3.5-397B-A17B
403Bqwen · 6 providers
API from $0.60 /1M inGPU from $3.50/hr
Devstral-Small-2-24B-Instruct-2512
24BMistral AI · 10 providers
API from $0.10 /1M inGPU from $0.28/hr
Qwen3-Next-80B-A3B-Instruct
81Bqwen · 7 providers
API from $0.14 /1M inGPU from $1.24/hr
Qwen2.5-VL-72B-Instruct
73Bqwen · 9 providers
API from $0.25 /1M inGPU from $1.13/hr
GLM-4.7
358BZyphra · 9 providers
API from $0.60 /1M inGPU from $3.50/hr
MiniMax-M2
229Bminimaxai · 8 providers
API from $0.26 /1M inGPU from $1.24/hr
Nebius
AWS
Azure
Verda
CoreWeave
OVHcloud