Lyber
Request access

Uncensored · FP8 · Approved early access

Uncensored · FP8 DeepSeek V4.1 Flash 1017 API

DeepSeek V4.1 Flash 1017 with modified uncensored · fp8 weights, one of the two checkpoints offered by Lyber. Check live readiness, then call it by its exact model ID through the same OpenAI-compatible API, API key and prepaid credit as every other model.

Choose MiniMax M3.1 Flash or DeepSeek V4.1 Flash 1017 by its exact model ID. Every answer names its model.

Model facts

Model ID
deepseek-v4.1-flash-1017-abliterated
Weights
Uncensored · FP8
Published rate snapshot
$0.20 / $0.80USD per 1 million tokens · fresh input / outputCached input: $0.20 per 1M tokens
Served precision
FP8 · explicit checkpoint
Access
Approved account access. Live Router metadata supplies current readiness, supported features and immutable billing version.
Status
Approved early access

These are the two offered checkpoints. Availability can change; the Router’s current published price version governs billing.

Call it with an OpenAI SDK.

Set the base URL to Lyber and pass this model ID. The response's model field names the model that answered.

chat.py
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://lyber-paid-acceptance-gateway-production.up.railway.app/v1",
    api_key=os.environ["LYBER_API_KEY"],
)

reply = client.chat.completions.create(
    model="deepseek-v4.1-flash-1017-abliterated",
    messages=[
        {"role": "user", "content": "Answer what I asked."},
    ],
)
print(reply.model)
print(reply.choices[0].message.content)

We work directly with model researchers and verify modified weights, commercial hosting rights, features and completed answers. Each served model’s identity stays explicit. We never substitute another model for your explicit choice.

The rest of the lineup

Full models & pricing →Connect a clientGet API access