Inference provider

Together

Headquarters: US

20

models

20

endpoints

Together website preview
Together website

Catalogue

Available models

ModelEndpointContextInput /MOutput /MCached input /MCache write /MUptime 1d
DeepSeek V4 Flash 0731together1.0M$0.14$0.28$0.03—93.81%
DeepSeek V4 Pro 0813together1.0M$1.32$3.96$0.13—91.92%
DeepSeek V4.1 Flashtogether1.0M$0.30$1.20$0.006—92.08%
GLM 5.2together1.0M$1.40$4.40$0.26—97.14%
GLM 5.3together1.0M$1.40$4.40$0.26—99.65%
GLM 5.3 Flashtogether1.0M$0.15$0.50$0.03—92.99%
Inklingtogether524K$1.00$4.05$0.17—97.41%
Kimi K3together1.0M$3.00$15.00$0.30—99.85%
Kokoro 82Mtogether4K$4.00$0.00——100.00%
Llama 3.3 70B Instructtogether131K$1.04$1.04——95.67%
MiniMax M3together524K$0.30$1.20$0.06—100.00%
Muse Glimmer 30Btogether131K$0.35$1.50$0.04—80.46%
Orpheus 3Btogether4K$15.00$0.00——100.00%
Parakeet TDT 0.6B v3together—$25.00$0.00——100.00%
Qwen3.5-9Btogether262K$0.17$0.25——93.26%
Qwen3.8 2.4T A95Btogether1.0M$2.00$6.00$0.25—97.13%
Tev1 4B Experimentaltogether33K$0.04$0.00——82.23%
Whisper Large V3together—$25.00$0.00——99.74%
gpt-oss-120btogether131K$0.15$0.60——100.00%