theserverless.dev InferenceList

Models

Showing 1–19 of 19 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Z.ai: GLM 5.3 Flash
Cheaper on Relace (−78.2%)
Z.ai text image video $0.0489/1M $0.0701/1M 1.0M
Google: Gemma 4 26B A4B
Cheaper on PrimeIntellect (−82.9%)
Google image text video $0.0765/1M $0.255/1M 262K
Qwen: Qwen3.6 35B A3B
Cheaper on Darkbloom (−29.2%)
Alibaba text image video $0.1/1M $0.9/1M 262K
Qwen: Qwen3.5-35B-A3B
Cheaper on DeepInfra (−20.6%)
Alibaba text image video $0.14/1M $1/1M 262K
Xiaomi: MiMo-V2.6-Flash
Cheaper on Relace (−36%)
Xiaomi text image video audio $0.14/1M $0.28/1M 1.1M
MiniMax: MiniMax M3.1 Flash
Cheaper on SambaNova (−60%)
MiniMax text image video $0.15/1M $0.6/1M 1.0M
NVIDIA: Nemotron 3.5 Super VL
Cheaper on Darkbloom (−44.2%)
NVIDIA text image video $0.15/1M $0.5/1M 1.0M
Qwen: Qwen3.8 27B
Cheaper on Chutes (−64.3%)
Alibaba text image video $0.15/1M $1.875/1M 1M
Qwen: Qwen3.8 Flash
Cheaper on DeepInfra (−21.6%)
Alibaba text image video $0.15/1M $0.47/1M 1M
Qwen: Qwen3.5-9B
Cheaper on PrimeIntellect (−70%)
Alibaba text image video $0.17/1M $0.25/1M 262K
MoonshotAI: Kimi K3
Cheaper on Inference.net (−65%)
Moonshot AI text image video $0.192/1M $15/1M 1.0M
Google: Gemma 4 31B
Cheaper on CoreWeave (−36%)
Google image text video $0.2/1M $0.4/1M 262K
Qwen: Qwen3.5-27B
Cheaper on SiliconFlow (−18.6%)
Alibaba text image video $0.26/1M $2.6/1M 262K
MiniMax: MiniMax M3
Cheaper on DeepInfra (−26.1%)
MiniMax text image video $0.3/1M $1.2/1M 1.0M
Qwen: Qwen3.6 27B
Cheaper on Chutes (−32.1%)
Alibaba text image video $0.32/1M $3.2/1M 262K
Xiaomi: MiMo-V2.5
Cheaper on AtlasCloud (−78.1%)
Xiaomi text audio image video $0.4/1M $2/1M 1.1M
Xiaomi: MiMo-V2.6-Pro
Cheaper on GMICloud (−15%)
Xiaomi text image video audio $0.435/1M $0.87/1M 1.1M
Google: Gemini 2.5 Pro
Cheaper on Oracle Cloud (−27.3%)
Google text image audio video $1.25/1M $10/1M 1.0M
MoonshotAI: Kimi K3.1 Pro
Cheaper on Inference.net (−10%)
Moonshot AI text image video $2/1M $10/1M 1.0M

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