How much does nace-ai/drex-v1.5 cost?
$0.04/M input tokens, output tokens free. Cost = round(input tokens × input price/M); settled exactly against upstream usage.
Prices synced from this gateway’s /v1/models feed at build time (regenerated on every deploy). Output tokens are free on every model in the catalog.
cost = round(input_tokens × input_price/M)Drex is Nace.AI’s decision-model family focused on enterprise judgment workloads; the Drex Max, v2.0 and v1.5 checkpoints are all on sale here.
Nace.AI: Drex v1.5
from typesafe_sdk import TypeSafeClient
client = TypeSafeClient(
base_url="https://api.easyjev.online",
api_key="sk-...",
)
resp = client.system_one(
state=state,
questions=questions,
model="nace-ai/drex-v1.5",
)
# resp.answers —— 结构化判定:概率 / 选项分布 / 有序分数curl https://api.easyjev.online/v1/systemone \
-H "Authorization: Bearer sk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "nace-ai/drex-v1.5",
"state": {"user": {"plan": "pro"}},
"questions": {
"is_premium": {"type": "noul", "criteria": {"true": "…", "false": "…"}}
}
}'$0.04/M input tokens, output tokens free. Cost = round(input tokens × input price/M); settled exactly against upstream usage.
Yes — swap base_url to https://api.easyjev.online and use an sk- key from this site; the request shape and typed answers are unchanged.
Yes — the Playground runs any model in the catalog against your own state and questions, billed to your balance with per-run cost shown.
The whole catalog shares one endpoint — model is a per-request field, no migration needed.