theserverless.dev InferenceList

Models

Showing 1–50 of 98 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Llama 3.1 8B Instruct Novita text $0.02/1M $0.05/1M 16K
Llama 3.2 1B Instruct Novita text $0.02/1M $0.02/1M 131K
PaddleOCR VL Novita text image $0.02/1M $0.02/1M 16K
DeepSeek OCR 2 Novita text image $0.03/1M $0.03/1M 8K
AutoGLM Phone 9B Multilingual Novita text image $0.035/1M $0.138/1M 66K
Gemma 3 12B Novita text image $0.05/1M $0.1/1M 131K
Llama 3 8B Stheno V3.2 Novita text $0.05/1M $0.05/1M 8K
NVIDIA Nemotron 3 Nano 30B A3B Novita text $0.05/1M $0.2/1M 262K
OpenAI GPT OSS 120B Novita text image $0.05/1M $0.25/1M 131K
DeepSeek R1 Distill Qwen3 8B 0528 Novita text $0.06/1M $0.09/1M 128K
Ling 3.0 Flash Novita text $0.06/1M $0.18/1M 262K
Baichuan M2 32B Novita text $0.07/1M $0.07/1M 131K
GLM 4.7 Flash Novita text $0.07/1M $0.4/1M 200K
Ling 3.0 Flash Fin Novita text $0.075/1M $0.22/1M 262K
Ling 3.0 Flash Sante Novita text $0.075/1M $0.22/1M 262K
Ling 3.0 Flash VL Novita text image video $0.075/1M $0.22/1M 262K
MythoMax L2 13B Novita text $0.09/1M $0.09/1M 4K
Gemma 3 27B Novita text image $0.119/1M $0.2/1M 98K
Gemma 4 26B A4B Novita text image $0.13/1M $0.4/1M 262K
GLM 4.5 Air Novita text $0.13/1M $0.85/1M 131K
Llama 3.3 70B Instruct Novita text $0.135/1M $0.4/1M 12K
Gemma 4 31B Novita text image $0.14/1M $0.4/1M 262K
Hermes 2 Pro Llama 3 8B Novita text $0.14/1M $0.14/1M 8K
Hy3 Novita text $0.14/1M $0.58/1M 262K
MiMo V2.6 Flash Novita text image video audio $0.14/1M $0.28/1M 1.0M
GLM 5.3 Flash Novita text image video $0.15/1M $0.5/1M 1.0M
MiniMax M3.1 Flash Novita text image video $0.15/1M $0.6/1M 1M
Qwen3.8 Flash Novita text image video $0.15/1M $0.47/1M 1M
Llama 4 Scout Instruct Novita text image $0.18/1M $0.59/1M 131K
Qwen3 VL 30B A3B Instruct Novita text video image $0.2/1M $0.7/1M 131K
Step 3.7 Flash Novita text image video $0.2/1M $1.15/1M 262K
Macaron V1 Tall Novita text $0.2475/1M $1.43/1M 262K
Qwen3.6 35B A3B Novita text image video $0.248/1M $1.485/1M 262K
Qwen MT Plus Novita text $0.25/1M $0.75/1M 16K
Qwen3 Omni 30B A3B Thinking Novita text audio video image $0.25/1M $0.97/1M 66K
Qwen3.5 35B A3B Novita text image video $0.25/1M $2/1M 262K
Llama 4 Maverick Instruct Novita text image $0.27/1M $0.85/1M 1.0M
CoBuddy Novita text $0.28/1M $1.13/1M 131K
DeepSeek V4.1 Flash Novita text image $0.3/1M $1.2/1M 1.0M
DeepSeek V4.1 Flash Novita text image $0.3/1M $1.2/1M 1.0M
DeepSeek V4.1 Flash 1017 Novita text image $0.3/1M $1.2/1M 1.0M
DeepSeek V4.1 Flash DST Novita text image $0.3/1M $1.2/1M 1.0M
GLM 4.6V Novita text video image $0.3/1M $0.9/1M 131K
Ling 3.1 Flash 1019 Novita text $0.3/1M $0.9/1M 1M
MiniMax M2.5 Novita text $0.3/1M $1.2/1M 205K
MiniMax M2.7 Novita text $0.3/1M $1.2/1M 205K
MiniMax M3 Novita text image video $0.3/1M $1.2/1M 1M
Qwen3.5 27B Novita text image video $0.3/1M $2.4/1M 262K
Qwen3.5 122B A10B Novita text image video $0.4/1M $3.2/1M 262K
Qwen3.8 27B Novita text image video $0.42/1M $3/1M 1M

Token rates are USD per 1M tokens. A dash means the source did not publish that amount. A zero is a real zero.