Qwen · Open weights
Qwen2 72B Dracarys
A Qwen2 72B Instruct finetune by Abacus.AI focused on improving coding performance.
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.49
- Output
- $0.49
Reference prices as published by the model provider. API example
Specifications
- Context window
- 32.8K
- Max output
- 8.2K
- Average output (7 days)
- 138 tokens
- Longer than 14% of 468 models
Side by side
Qwen2 72B Dracarys compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Qwen2 72B DracarysQwenThis model | WizardLM-2 8x22BmicrosoftRemove | |
|---|---|---|
| Provider | Qwen | microsoft |
| Discovery tier | Open weights | Open weights |
| Added | Aug 2, 2025 | Apr 15, 2025 |
| Limits | ||
| Context window | 32.77K | 65.54KBest |
| Max output | 8.19K | 8.19K |
| Average output | 138 tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.49 | $0.49 |
| Output | $0.49 | $0.49 |
| Performance | ||
| Request success (24h) | 23.8% | — |
| Capabilities | ||
| PDF input | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
There are no public benchmark results for these models yet.
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Request success (24h)
- 23.8%
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "abacusai/Dracarys-72B-Instruct",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="abacusai/Dracarys-72B-Instruct",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Qwen
Related models
Other Qwen models, starting with the same family.