theserverless.dev InferenceList

Models

Showing 1–14 of 14 · Sorted by input price, low to high.

Cheaper elsewhere
More filters
Io Net × Clear
Model Provider Modality Input ↑ Output Context
Google: Gemma 4 26B A4B Io Net text image $0.106/1M $0.328/1M 262K
Qwen: Qwen3.6 35B A3B Io Net text image video $0.12/1M $1.014/1M 262K
Xiaomi: MiMo-V2.6-Flash Io Net text image $0.143/1M $0.294/1M 1.0M
Z.ai: GLM 5.3 Flash Io Net text image $0.15/1M $0.88/1M 262K
NVIDIA: Nemotron 3.5 Super VL Io Net text image video $0.16/1M $0.48/1M 262K
DeepSeek: DeepSeek V4.1 Flash Io Net text image $0.2526/1M $1.074/1M 1.0M
Meta-Llama: Llama 4 Maverick 17B 128E Instruct FP8 Io Net text image $0.2687/1M $0.8263/1M 430K
Google: Gemma 4 31B Instruct Io Net text image $0.301/1M $0.68/1M 262K
Qwen: Qwen3.6 27B Io Net text image video $0.343/1M $3.12/1M 33K
Qwen: Qwen3.8 27B Io Net text image video $0.426/1M $2.518/1M 66K
MoonshotAI: Kimi K2.5 Io Net text image $0.5384/1M $2.835/1M 262K
MoonshotAI: Kimi K2.6 Io Net text image $0.7448/1M $3.582/1M 262K
MoonshotAI: Kimi K2.7 Code Io Net text image $0.802/1M $3.62/1M 262K
MoonshotAI: Kimi K3 Io Net text image $2.523/1M $17.264/1M 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.