Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Decisions uses GPT-6 Luna to evaluate shared text or image evidence against typed questions. It returns probabilities, fixed choices, or rubric scores for low-latency classification, routing, and prioritization workflows.
Jev 1.14 is TypeSafe's structured evaluation model. It evaluates one state against typed Noul, Choice, Score, and Box questions and returns calibrated answers with probabilities and confidence. Image inputs and Box questions are beta and dreamer-ready, not recommended for production.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Decisions
client.chat.completions.create(
model="openai/decisions",
messages=[{"role":"user","content":"hello"}],
)
# Jev 1.14
client.chat.completions.create(
model="typesafe/jev-1.14.0",
messages=[{"role":"user","content":"hello"}],
)