theserverless.dev InferenceList

Models

Showing 1–17 of 17 · Sorted by input price, low to high.

More filters
Model Provider Modality Input ↑ Output Context
Decision Small Tinfoil text $0.02/1M Not published— 33K
Nomic Embed Text Tinfoil text $0.05/1M Not published— 8K
Decision Medium Tinfoil text $0.06/1M Not published— 33K
GPT-OSS 120B Tinfoil text $0.15/1M $0.6/1M 131K
GPT-OSS Safeguard 120B Tinfoil text $0.15/1M $0.6/1M 131K
Voxtral Small 24B Tinfoil text $0.2/1M $0.6/1M 33K
Decision Large Tinfoil text $0.4/1M Not published— 33K
Gemma 4 31B Tinfoil text image $0.4/1M $1/1M 262K
DeepSeek V4.1 Flash Tinfoil text image $0.65/1M $1.45/1M 1.0M
Llama 3.3 70B Tinfoil text $1.75/1M $2.75/1M 131K
GLM-5.3 Tinfoil text $1.8/1M $5.75/1M 1.0M
Kimi K3 Tinfoil text image $4/1M $20/1M 262K
Privacy Filter Tinfoil text $10/1M Not published— 8K
Qwen3-TTS 1.7B Tinfoil text Not published— Not published— —
Voxtral Mini 4B Realtime Tinfoil text Not published— Not published— —
Voxtral TTS Tinfoil text Not published— Not published— —
Whisper Large V3 Turbo Tinfoil text Not published— Not published— —

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