---
title: "DeepSeek V3.2 API pricing"
canonical: https://uplinkswitch.ai/models/deepseek-v3.2
generated: 2026-10-25T13:47:11.532Z
source: https://api.uplinkswitch.com/v1/catalog
base_url: https://api.uplinkswitch.com/v1
---

# DeepSeek V3.2 API pricing

DeepSeek V3.2 API at $1.08/M input and $1.68/M output tokens. Works with the OpenAI SDK.

## Price per million tokens (USD)

| Tokens | DeepSeek list price | UplinkSwitch | Under list |
| --- | --- | --- | --- |
| Input | — | $1.08 | — |
| Cached input | — | $0.54 | — |
| Output | — | $1.68 | — |

## DeepSeek V3.2 vs DeepSeek V3.1 price (USD per million tokens)

| Tokens | DeepSeek V3.1 | DeepSeek V3.2 | Change |
| --- | --- | --- | --- |
| Input | $1.08 | $1.08 | same |
| Cached input | input rate | $0.54 | — |
| Output | $4.00 | $1.68 | -58% |

## Model

- Model id: `deepseek-v3.2`
- Formats: OpenAI SDK
- Base URL: https://api.uplinkswitch.com/v1
- Daily real-model check: Steady since Oct 20 (https://uplinkswitch.ai/proof#deepseek-v3.2)

## DeepSeek V3.2 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-v3.2 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-v3.2",
    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-v3.2',
  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-v3.2","messages":[{"role":"user","content":"Hello"}]}'
```

## Questions

### What is DeepSeek V3.2?

DeepSeek V3.2 is a model from DeepSeek. Through UplinkSwitch it answers the OpenAI SDK on one key as deepseek-v3.2.

### How much does the DeepSeek V3.2 API cost?

$1.08 per million input tokens and $1.68 per million output tokens, with cached input at $0.54.

### Is DeepSeek V3.2 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 $0.0019.

### What is the DeepSeek V3.2 model id?

deepseek-v3.2. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

### How do I get a DeepSeek V3.2 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 V3.2 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 V3.2?

Every day each model gets the same test prompt, and the results are public on /proof. DeepSeek V3.2's latest result: Steady since Oct 20.

### How does DeepSeek V3.2 pricing compare with DeepSeek V3.1?

Per million tokens here, DeepSeek V3.2 is $1.08 input and $1.68 output; DeepSeek V3.1 is $1.08 and $4.00. One key calls both, so switching is a change of model id.

### Is there a DeepSeek V3.2 API?

Yes: deepseek-v3.2 on the OpenAI format at https://api.uplinkswitch.com/v1, $1.08 input and $1.68 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

### How many parameters does DeepSeek V3.2 have?

671B total, 37B active per token, per deepseek-ai/DeepSeek-V3.2.

### What is DeepSeek V3.2's context window?

128K tokens, per deepseek-ai/DeepSeek-V3.2.

### Is DeepSeek V3.2 open source?

Its weights are open on Hugging Face (deepseek-ai/DeepSeek-V3.2); the license is MIT.

### What does DeepSeek V3.2 cost per 100 messages?

$0.30 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.08 input and $1.68 output per million tokens, from prepaid credit with no subscription.

### DeepSeek V3.2 or DeepSeek V3.2 Exp?

V3.2 is the release; V3.2 Exp is the September 2025 experiment that introduced its sparse attention. DeepSeek V3.2 is $1.08 / $1.68 per million tokens in / out, $3.00 for 1,000 chat turns; DeepSeek V3.2 Exp is $1.08 / $1.64 per million tokens in / out, $2.98 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.

## Related

- DeepSeek API pricing: https://uplinkswitch.ai/pricing/deepseek
- Cursor setup: https://uplinkswitch.ai/guides/cursor
- Cline setup: https://uplinkswitch.ai/guides/cline
- Roo Code setup: https://uplinkswitch.ai/guides/roo-code
- Kilo Code setup: https://uplinkswitch.ai/guides/kilo-code
- 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