DeepSeek · Efficient
DeepSeek V4.1 Flash 1017 Abliterated Thinking
An abliterated (refusal-removed) version of DeepSeek V4.1 Flash 1017. Text only, with tool calling, optional reasoning and a 1M-token context window. Its behavior may differ from DeepSeek V4.1 Flash 1017. Served by a single host; it may be unavailable while that host is down.
- Reasoning
- Tools
- Input
- Text
- Output
- Text
- Reasoning effort
- none · high
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.38
- Output
- $1.50
- Cache read
- $0.0075
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 131.1K
Side by side
DeepSeek V4.1 Flash 1017 Abliterated Thinking compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| DeepSeek V4.1 Flash 1017 Abliterated ThinkingDeepSeekThis model | GLM 4.6 Derestricted v5Z.aiRemove | |
|---|---|---|
| Provider | DeepSeek | Z.ai |
| Discovery tier | Efficient | Open weights |
| Added | Nov 16, 2026 | Dec 23, 2025 |
| Limits | ||
| Context window | 1MBest | 131.07K |
| Max output | 131.07K | — |
| Pricing, USD per 1M tokens | ||
| Input | $0.38Best | $0.40 |
| Output | $1.50 | $1.50 |
| Cache read | $0.0075Best | $0.20 |
| Performance | ||
| Throughput | 41.3 tok/sBest | 29.4 tok/s |
| Time to first token | 4.8 sBest | 11.5 s |
| Request success (24h) | 95.6%Best | 79.9% |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Reasoning effort | none, high | 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
- 41.3 tok/s
- Faster than 32% of 52 models
- Time to first token
- 4.8 s
- Quicker than 28% of 52 models
- Prompt cache hits
- 95.2%
- About $0.0251 per 1M input tokens with caching
- Request success (24h)
- 95.7%
- 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": "deepseek/deepseek-v4.1-flash-1017-abliterated:thinking", "reasoning_effort": "none", "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="deepseek/deepseek-v4.1-flash-1017-abliterated:thinking", messages=[{"role": "user", "content": "Explain this stack trace."}],)print(reply.choices[0].message.content)DeepSeek
Related models
Other DeepSeek models, starting with the same family.