DeepSeek V4.1 Flash 1017 Abliterated API
Model ID: deepseek-v4.1-flash-1017-abliterated · Developer: DeepSeek · Available on 7API: yes, as of 2026-11-20
An abliterated DeepSeek V4.1 Flash with an adjustable effort scale (none, low, high, max). Defaults to high. The older deepseek-v4.1-flash-abliterated ID remains accepted.
DeepSeek V4.1 Flash 1017 Abliterated is an abliterated version of DeepSeek V4.1 Flash 1017, available through 7API's uncensored AI API. Call DeepSeek V4.1 Flash 1017 Abliterated with any OpenAI- or Anthropic-compatible client. Use base URL https://7api.st/v1 (OpenAI) or https://7api.st (Anthropic) and send "model": "deepseek-v4.1-flash-1017-abliterated".
Specifications
| Model ID | deepseek-v4.1-flash-1017-abliterated |
| Context window | 1,000,000 tokens |
| Max output | 65,536 tokens |
| Input | Text |
| Tool calling | Yes |
| Streaming | Yes |
| Reasoning effort | none, low, high, max (default high) |
| API formats | Chat Completions, Responses, Anthropic Messages |
Pricing
| USD per 1M tokens | |
|---|---|
| Input | $0.15 |
| Output | $0.15 |
| Cached input | $0.05 |
For example, an agent turn with 150,000 cached input tokens, 2,000 new input tokens and 800 output tokens costs about $0.0079 on DeepSeek V4.1 Flash 1017 Abliterated. Billing is pay per token from a prepaid balance. See Pricing and billing.
Benchmarks
Independent leaderboards don't test abliterated builds. The base model, DeepSeek V4.1 Flash 1017, scores 45 on the Artificial Analysis Intelligence Index at max effort. Expect DeepSeek V4.1 Flash 1017 Abliterated to be close to that on general tasks, and test it on your own prompts.
DeepSeek V4.1 Flash 1017 Abliterated vs. other DeepSeek models
| Model | Type | Based on | Input / 1M | Output / 1M | Cached / 1M | Max output | Reasoning effort |
|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | Standard | — | $0.02 | $0.02 | $0.005 | 66K | model default |
| DeepSeek V4.1 Flash 1017 Abliterated | Abliterated | DeepSeek V4.1 Flash 1017 | $0.15 | $0.15 | $0.05 | 66K | none low high max |
| DeepSeek V4.1 Flash 1017 Abliterated Fast | Abliterated | DeepSeek V4.1 Flash 1017 | $0.70 | $0.70 | $0.16 | 66K | model default |
Example
from openai import OpenAI
client = OpenAI(base_url="https://7api.st/v1", api_key="YOUR_7API_KEY")
r = client.chat.completions.create(
model="deepseek-v4.1-flash-1017-abliterated",
messages=[{"role": "user", "content": "Write a haiku about caching."}],
)
print(r.choices[0].message.content)In Claude Code: /model claude-deepseek-v4.1-flash-1017-abliterated. Setup guides: Claude Code, OpenCode, Codex, Cursor.
Related models
- DeepSeek V4.1 Flash 1017 Abliterated Fast: $0.70/M, $0.16/M cached, 1M context
- DeepSeek V4.1 Flash: $0.02/M, $0.005/M cached, 1M context
- DeepSeek V4.1 Flash 1017: $0.02/M, $0.005/M cached, 1M context
- DeepSeek V4.1 Flash 1017 HQ: $0.05/M, $0.01/M cached, 1M context
- DeepSeek V4 Flash: $0.03/M, $0.0027/M cached, 1M context
- DeepSeek V4 Pro: $0.25/M, $0.05/M cached, 1M context
- All uncensored and abliterated models
- What is abliterated AI?
Is there an abliterated DeepSeek model?
Yes. deepseek-v4.1-flash-1017-abliterated is an abliterated DeepSeek V4.1 Flash with an adjustable effort scale from none to max.
Also searched as: DeepSeek V4.1 Flash 1017 Abliterated, abliterated DeepSeek, deepseek-v4.1-flash-1017-abliterated.
