- Input
- $0.04
- Output
- $0.00
nace-aiListed Oct 8, 2026
drex-v1.5
Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single…
Source description
Drex v1.5 is a 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated probability for every option in a single forward pass, with no text generation. It is TypeSafe System One compatible, handles contexts up to 131K tokens, and scores 58.28 on Decision Index 0.2.1, ahead of Jev 1.13.0.
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
2 quotesPrices across providers
Your token mix
USD · listed token rates- Input
- $0.04
- Output
- $0.00
Model specifications
- Developer
- nace-ai
- Modality
- Decision
- Context
- 131,072 tokens
- Maximum output
- 117,964 tokens
- Weights
- Open weights
- Provider listed
- Oct 8, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
nace-ai/drex-v1.5 - deepinfra
nace-ai/drex-v1.5
Sources
Updated Oct 18, 2026
More from nace-ai
View all ↗nace-aiListed 5 days ago
Nace.AI: Drex v2.0
Self-hosted decision scoring via Python or dedicated llama.cpp/Ollama forks; returns option probabilities without prose.
131.1K contextNo reported score
No reported score
nace-aiListed 9 days ago
drex-v2.0
Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated…
131.1K contextNo reported score
No reported score