Qwen · Open weights
DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic
xtools-at's uncensored Heretic version of Jackrong's DeepSeek V4 Pro Qwen3.5 9B, a Qwen3.5 9B model distilled from DeepSeek V4 Pro on about 250,000 math and STEM samples. It answers directly without a thinking phase. It accepts and returns text, with a 32,768-token context window shared by input and output and up to 8,192 output tokens.
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.28
- Output
- $0.28
- Cache read
- $0.14
Reference prices as published by the model provider. API example
Specifications
- Context window
- 32.8K
- Max output
- 8.2K
Side by side
DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| DeepSeek V4 Pro Qwen3.5 9B Uncensored HereticQwenThis model | Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled DerestrictedQwenRemove | |
|---|---|---|
| Provider | Qwen | Qwen |
| Discovery tier | Open weights | Open weights |
| Added | Nov 7, 2026 | May 15, 2026 |
| Limits | ||
| Context window | 32.77K | 262.14KBest |
| Max output | 8.19K | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.28Best | $0.31 |
| Output | $0.28Best | $0.31 |
| Cache read | $0.14 | $0.0306Best |
| Cache write | — | $0.38 |
| Performance | ||
| Throughput | 68.3 tok/sBest | 36.0 tok/s |
| Time to first token | 86.1 s | 4.2 sBest |
| Request success (24h) | 100.0%Best | 84.1% |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | No | Yes |
| Vision | No | Yes |
| Reasoning effort | — | none, high |
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.
- Throughput
- 68.3 tok/s
- Faster than 40% of 52 models
- Time to first token
- 86.1 s
- Quicker than 0% of 52 models
- Prompt cache hits
- 0.0%
- About $0.28 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Ophiris’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.ophiris.xyz/api/v1/chat/completions \ -H "Authorization: Bearer $OPHIRIS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic", "messages": [{ "role": "user", "content": "Explain this stack trace." }] }'import osfrom openai import OpenAI client = OpenAI(base_url="https://www.ophiris.xyz/api/v1", api_key=os.environ["OPHIRIS_API_KEY"])reply = client.chat.completions.create( model="xtools-at/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic", 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.