# DeepSeek V3.2 API Pricing

As of October 10, 2026, DeepSeek V3.2 costs $0.28 per 1M input tokens and $0.40 per 1M output tokens on DeepSeek, with cache reads at $0.028 per 1M tokens. Across 10 providers on LiteLLM, the input price ranges from $0.26 to $3.00. It has a 163,840-token context window and returns up to 163,840 tokens per response.

- Page: https://models.litellm.ai/models/deepseek-v3.2
- Lab: DeepSeek
- LiteLLM model name: `deepseek/deepseek-v3.2`
- Context window: 163,840 tokens
- Max output: 163,840 tokens
- Added to LiteLLM: December 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| DeepSeek | `deepseek/deepseek-v3.2` | $0.28 | $0.40 | $0.028 | – | – | 160K |
| Amazon Bedrock | `deepseek.v3.2` | $0.62 | $1.85 | – | – | – | 164K |
| Azure AI Foundry | `azure_ai/deepseek-v3.2` | $0.58 | $1.68 | – | – | – | 128K |
| DeepInfra | `deepinfra/deepseek-ai/DeepSeek-V3.2` | $0.26 | $0.38 | $0.13 | – | – | 160K |
| Fireworks AI | `fireworks_ai/accounts/fireworks/models/deepseek-v3p2` | $0.56 | $1.68 | – | – | – | 160K |
| FriendliAI | `friendliai/deepseek-ai/DeepSeek-V3.2` | $0.50 | $1.50 | $0.25 | – | – | 160K |
| GMI Cloud | `gmi/deepseek-ai/DeepSeek-V3.2` | $0.28 | $0.40 | – | – | – | 160K |
| Google Vertex AI | `vertex_ai/deepseek-ai/deepseek-v3.2-maas` | $0.56 | $1.68 | $0.056 | – | – | 160K |
| Novita AI | `novita/deepseek/deepseek-v3.2` | $0.269 | $0.40 | $0.1345 | – | – | 160K |
| SambaNova | `sambanova/DeepSeek-V3.2` | $3.00 | $4.50 | – | – | – | 32K |
| Amazon Bedrock (ap-northeast-1) | `bedrock/ap-northeast-1/deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (ap-south-1) | `bedrock/ap-south-1/deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (ap-southeast-3) | `bedrock/ap-southeast-3/deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (eu-north-1) | `bedrock/eu-north-1/deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (sa-east-1) | `bedrock/sa-east-1/deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (us-east-1) | `bedrock/us-east-1/deepseek.v3.2` | $0.62 | $1.85 | – | – | – | 160K |
| Amazon Bedrock (us-east-2) | `bedrock/us-east-2/deepseek.v3.2` | $0.62 | $1.85 | – | – | – | 160K |
| Amazon Bedrock (us-west-2) | `bedrock/us-west-2/deepseek.v3.2` | $0.62 | $1.85 | – | – | – | 160K |
| Amazon Bedrock (EU cross-region) | `eu.deepseek.v3.2` | $0.74 | $2.22 | – | – | – | 160K |
| Amazon Bedrock (US cross-region) | `us.deepseek.v3.2` | $0.62 | $1.85 | – | – | – | 160K |

## Cost examples

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

- DeepSeek: $0.76
- DeepInfra: $0.71
- Novita AI: $0.738
- GMI Cloud: $0.76

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

- DeepSeek: $2.88
- DeepInfra: $2.676
- Novita AI: $2.77
- GMI Cloud: $2.88

## Features

Supported: Function calling, Parallel tool calls, Structured output, Reasoning, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="deepseek/deepseek-v3.2",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

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

DeepSeek V3.2 costs $0.28 per 1M input tokens and $0.40 per 1M output tokens on DeepSeek, with cache reads at $0.028 per 1M tokens. Across 10 providers on LiteLLM, the input price ranges from $0.26 to $3.00.

### What is the context window of DeepSeek V3.2?

DeepSeek V3.2 has a 163,840-token context window and returns up to 163,840 tokens per response.

### Which providers offer DeepSeek V3.2?

DeepSeek V3.2 is available from 10 providers through LiteLLM: DeepSeek, Amazon Bedrock, Azure AI Foundry, DeepInfra, Fireworks AI, FriendliAI, GMI Cloud, Google Vertex AI, Novita AI and SambaNova. The lowest price is on DeepInfra.

### How do I call DeepSeek V3.2 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="deepseek/deepseek-v3.2", 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 V3.2 support?

DeepSeek V3.2 supports function calling, parallel tool calls, structured output, reasoning and prompt caching.

### When did LiteLLM add DeepSeek V3.2?

DeepSeek V3.2 was added to LiteLLM's model price file in December 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json