Nexevo exclusive capabilities
:fast / :cheap / :quality routing suffix
Add a suffix to the model name to give routing hints, without reorganizing the request body.
Python
python
# Append :fast / :cheap / :quality to the model name for routing hints.
# The router takes these as preferences (not hard constraints).
# "Use the fastest available variant"
client.chat.completions.create(
model="deepseek-chat:fast",
messages=[{"role": "user", "content": "Quick reply please"}],
)
# "Optimize for cost — pick the cheapest model that handles this difficulty"
client.chat.completions.create(
model="nexevo/fast",
messages=[{"role": "user", "content": "Translate to French: ..."}],
)
# "Optimize for quality — escalate to a stronger model if needed"
client.chat.completions.create(
model="nexevo/balanced",
messages=[{"role": "user", "content": "Hard reasoning problem..."}],
)