---
title: "DeepSeek V4 Pro Abliterated API pricing"
canonical: https://uplinkswitch.ai/models/deepseek-v4-pro-abliterated
generated: 2026-11-16T01:03:12.265Z
source: https://api.uplinkswitch.com/v1/catalog
base_url: https://api.uplinkswitch.com/v1
---

# DeepSeek V4 Pro Abliterated API pricing

DeepSeek V4 Pro Abliterated API at $1.00/M input and $4.00/M output tokens. 1,000,000-token context window. Works with the OpenAI SDK.

## Price per million tokens (USD)

| Tokens | DeepSeek list price | UplinkSwitch | Under list |
| --- | --- | --- | --- |
| Input | — | $1.00 | — |
| Cached input | — | $0.10 | — |
| Output | — | $4.00 | — |

## Model

- Model id: `deepseek-v4-pro-abliterated`
- Formats: OpenAI SDK
- Base URL: https://api.uplinkswitch.com/v1
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Daily real-model check: Steady since Nov 6 (https://uplinkswitch.ai/proof#deepseek-v4-pro-abliterated)

## DeepSeek V4 Pro Abliterated API key

1. Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
2. Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
3. Send deepseek-v4-pro-abliterated as the model. The same key calls every other model in the catalog.

## Request

### Python · OpenAI SDK

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="deepseek-v4-pro-abliterated",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
```

### TypeScript · OpenAI SDK

```typescript
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'deepseek-v4-pro-abliterated',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
```

### curl

```bash
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"deepseek-v4-pro-abliterated","messages":[{"role":"user","content":"Hello"}]}'
```

## DeepSeek V4 Pro Abliterated settings for SillyTavern and Janitor AI

- SillyTavern API: Chat Completion
- Chat Completion Source: Custom (OpenAI-compatible)
- Custom Endpoint (Base URL): https://api.uplinkswitch.com/v1
- Model ID: deepseek-v4-pro-abliterated
- Context (tokens): 1,000,000 tokens
- Max Response Length: 128,000 tokens
- Janitor AI proxy URL: https://api.uplinkswitch.com/v1/chat/completions
- Janitor AI model: deepseek-v4-pro-abliterated
- API key: your sk-uplink- key

A chat of 100 replies of 300 tokens costs $0.52 at 4,000 tokens of context and $1.72 at 16,000, at the live price; every message resends the context.

## Questions

### What is DeepSeek V4 Pro Abliterated?

DeepSeek V4 Pro Abliterated is a model from DeepSeek, with a 1,000,000-token context window. Through UplinkSwitch it answers the OpenAI SDK on one key as deepseek-v4-pro-abliterated.

### How much does the DeepSeek V4 Pro Abliterated API cost?

$1.00 per million input tokens and $4.00 per million output tokens, with cached input at $0.10.

### Is DeepSeek V4 Pro Abliterated free?

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.003.

### What is the DeepSeek V4 Pro Abliterated context window?

DeepSeek V4 Pro Abliterated has a 1,000,000-token context window, with up to 128,000 output tokens per request.

### What is the DeepSeek V4 Pro Abliterated model id?

deepseek-v4-pro-abliterated. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

### How do I get a DeepSeek V4 Pro Abliterated API key?

Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls DeepSeek V4 Pro Abliterated and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

### Is it the real DeepSeek V4 Pro Abliterated?

Every day each model gets the same test prompt, and the results are public on /proof. DeepSeek V4 Pro Abliterated's latest result: Steady since Nov 6.

### Is there a DeepSeek V4 Pro Abliterated API?

Yes: deepseek-v4-pro-abliterated on the OpenAI format at https://api.uplinkswitch.com/v1, $1.00 input and $4.00 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

### What is DeepSeek V4 Pro Abliterated based on?

No base model, parameter count or training notes are published for DeepSeek V4 Pro Abliterated. The catalog lists a 1,000,000-token context window and 128,000 max output tokens.

### Is DeepSeek V4 Pro Abliterated really uncensored?

DeepSeek V4 Pro Abliterated is served live on the OpenAI-compatible API at the same base URL and key as every other model, and it answers the prompts a filtered model declines. The daily real-model check at /proof confirms the model answering deepseek-v4-pro-abliterated is the live one.

### What does DeepSeek V4 Pro Abliterated cost per 100 messages?

$0.40 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.00 input and $4.00 output per million tokens, from prepaid credit with no subscription.

## Related

- Uncensored models on one key: https://uplinkswitch.ai/uncensored
- SillyTavern setup: https://relayswitch.io/guides/sillytavern
- Janitor AI setup: https://relayswitch.io/guides/janitorai
- Chub AI setup: https://relayswitch.io/guides/chub
- RisuAI setup: https://relayswitch.io/guides/risu
- SDKs setup: https://uplinkswitch.ai/guides/sdks
- Every model and price: https://uplinkswitch.ai/llms-full.txt
- Machine catalog: https://uplinkswitch.ai/ai-catalog.json
