LiteLLMLiteLLM/ MODELS

DeepSeek V4.1 Flash Abliterated API Pricing

By DeepSeek · 1 providerrefuseless/deepseek-v4.1-flash-abliteratedCompare
Input / output
$0.14 / $0.50 per 1M tokens
Cache read
$0.035 / 1M
Context
1M tokens
Max output
130K tokens

As of October 31, 2026, DeepSeek V4.1 Flash Abliterated costs $0.14 per 1M input tokens and $0.50 per 1M output tokens on Refuseless, with cache reads at $0.035 per 1M tokens. It has a 1,048,576-token context window and returns up to 130,000 tokens per response.

Prices updated Checked

DeepSeek V4.1 Flash Abliterated pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

DeepSeek V4.1 Flash Abliterated prices by provider in US dollars, token prices per 1M tokens, as of October 31, 2026. Source: LiteLLM model price file.
ProviderModel name in LiteLLMInputOutputCache readContext
Refuselessrefuseless/deepseek-v4.1-flash-abliterated$0.14$0.50$0.0351M

What DeepSeek V4.1 Flash Abliterated costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Refuseless$0.53

100 long-document requests with 100,000 input and 2,000 output tokens each

Refuseless$1.50

DeepSeek V4.1 Flash Abliterated cost calculator

At Refuseless's price ($0.14 input, $0.50 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $3.90 a day, about $117 a month. Change the numbers for your workload, or compare it with other models.

Per request
$0.00039
Per day
$3.90
Per month (30 days)
$117

DeepSeek V4.1 Flash Abliterated features

Input: text. Output: text.

Use DeepSeek V4.1 Flash Abliterated with LiteLLM

Call DeepSeek V4.1 Flash Abliterated through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="refuseless/deepseek-v4.1-flash-abliterated",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: deepseek-v4.1-flash-abliterated
    litellm_params:
      model: refuseless/deepseek-v4.1-flash-abliterated
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_API_KEY" \
  -d '{
    "model": "deepseek-v4.1-flash-abliterated",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

DeepSeek V4.1 Flash Abliterated FAQ

How much does DeepSeek V4.1 Flash Abliterated cost?

DeepSeek V4.1 Flash Abliterated costs $0.14 per 1M input tokens and $0.50 per 1M output tokens on Refuseless, with cache reads at $0.035 per 1M tokens.

What is the context window of DeepSeek V4.1 Flash Abliterated?

DeepSeek V4.1 Flash Abliterated has a 1,048,576-token context window and returns up to 130,000 tokens per response.

Which providers offer DeepSeek V4.1 Flash Abliterated?

DeepSeek V4.1 Flash Abliterated is available from Refuseless through LiteLLM, using the model name refuseless/deepseek-v4.1-flash-abliterated.

How do I call DeepSeek V4.1 Flash Abliterated with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="refuseless/deepseek-v4.1-flash-abliterated", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does DeepSeek V4.1 Flash Abliterated support?

DeepSeek V4.1 Flash Abliterated supports function calling, structured output, reasoning and prompt caching. It does not support image input.

When did LiteLLM add DeepSeek V4.1 Flash Abliterated?

DeepSeek V4.1 Flash Abliterated was added to LiteLLM's model price file on October 30, 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:

LiteLLM docs: Refuseless.

Provider pages: Refuseless.