JouleCloudinferenceresearchdocsplaygroundmodelspricingcalculatorstatus
Models / qwen2.5-7b-instruct

qwen2.5-7b-instructavailable

Qwen2.5 Instruct

General chat, drafting, extraction, RAG answers

Parameters7B
Context32K
HardwareRTX 3090
$0.20 input · $0.60 output per 1 million tokens

Call this model by setting the model field to qwen2.5-7b-instruct. See the full model list or model docs.