# DeepSeek: DeepSeek V3.2

- Model id: `deepseek/deepseek-v3.2`
- Served by: -
- List price per 1M tokens, input / output, from: -, with 0% platform fee. A request is billed at the list price of the host that served it.
- Context: 164K, max output 147K
- Prices read 2026-11-15 09:33 UTC
- Page: https://plaingateway.com/models/deepseek/deepseek-v3.2

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

## Hosts

| Host | Endpoint | In / out /M | Cache read /M | Context | Served |
|---|---|---|---|---|---|
| Gmicloud | `gmicloud/fp8` | $0.209 / $0.31 | $0.0216 | 164K | no |
| Atlas Cloud | `atlas-cloud/fp8` | $0.26 / $0.38 | $0.13 | 164K | no |
| DeepInfra | `deepinfra/fp4` | $0.26 / $0.38 | $0.13 | 164K | no |
| Baidu | `baidu/fp8` | $0.28 / $0.42 | $0.028 | 131K | no |
| Siliconflow | `siliconflow/fp8` | $0.259 / $0.80 | $0.14 | 164K | no |
| Digitalocean | `digitalocean` | $0.30 / $0.96 | $0.09 | 164K | no |

## First request

```sh
curl https://api.plaingateway.com/api/v1/chat/completions \
  -H "Authorization: Bearer $PLAINGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "deepseek/deepseek-v3.2", "messages": [{"role": "user", "content": "Say hello in five words."}]}'
```

Sign up at https://plaingateway.com/signup (no card), create a key, send a test call, and add credits when you want more. New accounts may get a small starting credit. The whole bootstrap for agents: https://plaingateway.com/llms.txt