eva-unit-01 · Open weights
EVA-Qwen2.5-32B-v0.2
A RP/storywriting specialist model, full-parameter finetune of Qwen2.5-32B on mixture of synthetic and natural data. It uses Celeste 70B 0.1 data mixture, greatly expanding it to improve versatility, creativity and flavor of the resulting model.
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.80
- Output
- $0.80
Reference prices as published by the model provider. API example
Specifications
- Context window
- 16.4K
- Max output
- 8.2K
- Average output (7 days)
- 238 tokens
- Longer than 25% of 468 models
Side by side
EVA-Qwen2.5-32B-v0.2 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| EVA-Qwen2.5-32B-v0.2eva-unit-01This model | Tencent Hy4 PreviewtencentRemove | |
|---|---|---|
| Provider | eva-unit-01 | tencent |
| Discovery tier | Open weights | Open weights |
| Added | Jul 26, 2025 | Aug 28, 2026 |
| Limits | ||
| Context window | 16.38K | 1.05MBest |
| Max output | 8.19K | 64KBest |
| Average output | 238 tokens | 2K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.80Best | $0.83 |
| Output | $0.80Best | $2.50 |
| Cache read | — | $0.042 |
| Performance | ||
| Throughput | — | 205.6 tok/s |
| Time to first token | — | 5.9 s |
| Request success (24h) | 41.3% | 99.8%Best |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | none, low, high |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- EVA-Qwen2.5-32B-v0.2
- Tencent Hy4 Preview
| Leaderboard | EVA-Qwen2.5-32B-v0.2 | Tencent Hy4 Preview |
|---|---|---|
| WebDev Overall | Not in top 20 | #15 · 1631.2 |
| WebDev · Webdev | Not in top 20 | #15 · 1631.2 |
| WebDev · Webdev-react | Not in top 20 | #13 · 1652.6 |
Ranks among Noumen catalog models on LMArena leaderboards. Only top-20 placements are listed.LMArena
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)
- 41.3%
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": "EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
"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="EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)eva-unit-01
Related models
Other eva-unit-01 models, starting with the same family.