impulse

DeepSeek V4.1 Flash Abliterated

Open weights
API id deepseek-v4.1-flash-abliterated
Input / 1M
$0.14
at Refuseless
Output / 1M
$0.50
at Refuseless
Context window
1M
tokens
Max output
130K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Refuseless, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.14$0.50
Cached input
75% off input
$0.035

What it costs a month

At Refuseless list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$70.05
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$60.00
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$110
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$456
Use your own numbers

Where to run it

1 host serve DeepSeek V4.1 Flash Abliterated. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
deepseek-v4.1-flash-abliterated
$0.14 / $0.50

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Effort settings the source lists
lowhighmax
Features
Prompt caching
Open weights
License: DeepSeek License (MIT code)
Runtimes: SGLang, TGI, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Refuseless.

Smaller DeepSeek models

No cheaper DeepSeek model keeps its key capabilities.

Other frontier labs

  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    13% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    13% less

Open-weight picks

Call it

Using Refuseless's API.

Python
from litellm import completion

response = completion(
    model="refuseless/deepseek-v4.1-flash-abliterated",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does DeepSeek V4.1 Flash Abliterated cost?

On Refuseless, DeepSeek V4.1 Flash Abliterated costs $0.14 per million input tokens and $0.50 per million output tokens. Cached input costs $0.035 per million tokens.

Which APIs offer DeepSeek V4.1 Flash Abliterated?

DeepSeek V4.1 Flash Abliterated runs on 1 API: Refuseless.

What is DeepSeek V4.1 Flash Abliterated's context window?

1M tokens, with up to 130K tokens in one reply.

Is DeepSeek V4.1 Flash Abliterated being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to DeepSeek V4.1 Flash Abliterated?

Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (13% less), GPT-6 Luna on OpenAI (13% less) and Qwen3.8 Omni Flash on Alibaba DashScope (0% less). Savings are on a mix of 3 input tokens to 1 output token.

What is DeepSeek V4.1 Flash Abliterated's API model id?

Use deepseek-v4.1-flash-abliterated with Refuseless.

Sources

Raw catalog entry for deepseek-v4.1-flash-abliterated on Refuseless
{
  "cache_read_input_token_cost": 3.5e-8,
  "input_cost_per_token": 1.4e-7,
  "litellm_provider": "refuseless",
  "max_input_tokens": 1048576,
  "max_output_tokens": 130000,
  "mode": "chat",
  "output_cost_per_token": 5e-7,
  "source": "https://refuseless.com/pricing",
  "supports_function_calling": true,
  "supports_prompt_caching": true,
  "supports_reasoning": true,
  "supports_response_schema": true,
  "supports_tool_choice": true,
  "supports_vision": false,
  "reasoning_effort_levels": [
    "low",
    "high",
    "max"
  ]
}