Fireworks AI exposes Drex v2.0 through model ID accounts/fireworks/models/drex-v2-0. Use the setup steps, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-22. Next refresh: weekly.
Quick Start
- 1
- 2Use the Fireworks AI SDK or REST API to call
accounts/fireworks/models/drex-v2-0— see the documentation for request format.
Code Examples
Install
pip install openaiAPI key
FIREWORKS_API_KEYModel ID
accounts/fireworks/models/drex-v2-0Fireworks model IDs use "accounts/fireworks/models/{model-name}" format, e.g. "accounts/fireworks/models/llama4-scout-instruct-basic" or "accounts/fireworks/models/deepseek-r1".
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["FIREWORKS_API_KEY"],
base_url="https://api.fireworks.ai/inference/v1"
)
response = client.chat.completions.create(
model="accounts/fireworks/models/drex-v2-0",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Capabilities
No model capability flags are currently sourced.
About Drex v2.0
Drex v2.0 is Nace.AI's open-weight decision model on Qwen3.6-35B-A3B with a Kev pointer head: it answers typed questions about a state with a probability per option in one forward pass. Runs locally via Python, llama.cpp or Ollama; Nace.AI Open RAIL-M license.
Model Specs
Released2026-10-06
Parameters35B total, 3B active
Context128K
ArchitectureMixture of Experts