Aplomb 1

by EmpirioLabs

Aplomb 1 is EmpirioLabs' 5.3-billion-parameter decision model, built on Alibaba's Qwen3.5-4B with an audio encoder from Qwen3-Omni. It reads text, JSON, images, audio and video and answers typed questions with calibrated probabilities rather than generated prose. The model supports a state plus its longest question of up to one million tokens. Questions can ask for a yes/no judgment, a choice among named options, a position on an ordered scoring rubric, or a tool selection. Tool answers include distributions for enum and boolean arguments; free-text arguments remain for the calling application to fill. Questions are evaluated independently, and an optional abstention result represents the probability that the input lacks the information needed to answer. Use it for classification, routing, moderation, extraction checks, agent tool selection and evaluation when software needs an answer with uncertainty attached. Aplomb 1 does not generate text. Its open weights are available under the EmpirioLabs Model License, which places conditions on commercial use and redistribution.

Call Aplomb 1 on Opper through the System One evaluation API. Sign up without a credit card. Get started

Key info

Input
Output
Features
Context window
1M
Max output
—
Input price
$0.02 /1M
Output price
$0 /1M
  • Zero data retention on pay-as-you-go
  • No training by default
  • GDPR DPA available

Available routes

Aplomb 1 runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutputCache read
MultiNo$0.02$0Input price

Live routes and prices as JSON: api.opper.ai/v3/models?q=empiriolabs%2Faplomb-1

Data handling per route

Each route hosting Aplomb 1 has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

EmpirioLabs — Multi-region

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. GLOBAL; SCCs; DPA available.

Zero data retention
Yes. Nothing is logged, held for abuse monitoring or used for training.
Training
No training on customer data.
Logging
None
Abuse monitoring
On by default, keeps nothing
Subprocessor access
No subprocessor reads content
GDPR DPA
DPA available
Transfer mechanism
SCCs

Benchmarks

Aplomb 1 played 100 games of Pac-Man against the four arcade ghosts.

JevMan: the Pac-Man benchmark for AI decision models

Watch Aplomb 1's JevMan game
Rank in our runs12 of 15
Mean score1,693
Best game3,520
Games100
See the JevMan benchmark →Compare all decision modelsScores from Opper's own runs. Updated Oct 24, 2026.

Get started

Call Aplomb 1 through the Opper gateway with one API key. Evaluate state against typed questions using TypeSafe’s System One API for yes/no decisions, classification, and rubric scoring.

See the Opper evaluation guide and the TypeSafe API reference for question types and response formats. Compare every decision model, on one API.

Aplomb 1 is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

curl https://api.opper.ai/v3/compat/v1/systemone \
-H "Authorization: Bearer $OPPER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "empiriolabs/aplomb-1",
"state": "The customer cannot sign in and needs help immediately.",
"questions": {
"is_urgent": {
"type": "noul",
"instructions": "Does the customer need urgent help?"
}
}
}'

Use Aplomb 1 in your apps

Pick your tool, then choose Aplomb 1 to see how to run it through Opper.

Compare Aplomb 1 with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation