# deepseek-ai/DeepSeek-V3.2-TEE

> DeepSeek-V3.2 is an open-source LLM optimized for efficient reasoning and agent tasks through sparse attention and reinforcement learning, useful for complex problem-solving and tool-use applications.

This file is intended for AI coding agents wiring an application to this specific Chutes model.

## Important URLs

- Model page: https://chutes.ai/app/chute/chutes-deepseek-ai-deepseek-v3-2-tee
- Model llms.txt: https://chutes.ai/app/chute/chutes-deepseek-ai-deepseek-v3-2-tee/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/chutes-deepseek-ai-deepseek-v3-2-tee/openapi.json
- Global Chutes llms.txt: https://chutes.ai/llms.txt
- Full Chutes docs export: https://chutes.ai/llms-full.txt
- Management API OpenAPI (account/billing/keys, NOT this model): https://api.chutes.ai/openapi.json

## Model Identifiers

- Name: `deepseek-ai/DeepSeek-V3.2-TEE`
- Chute ID: `398651e1-5f85-5e50-a513-7c5324e8e839`
- Slug: `chutes-deepseek-ai-deepseek-v3-2-tee`
- Owner: `chutes`

## Authentication

- Use `Authorization: Bearer $CHUTES_API_KEY` for inference calls.
- Send JSON request bodies with `Content-Type: application/json` unless the endpoint documentation says otherwise.
- The request body is FLAT — send the request fields at the top level (no `input_args`/`args` wrapper).
- This model is served on the shared OpenAI-compatible gateway. Set the request `model` field to the exact Name above (`deepseek-ai/DeepSeek-V3.2-TEE`), and use base URL `https://llm.chutes.ai/v1`.
- For base64 media fields, send raw base64 strings in API requests. The web playground may use temporary Blob upload references internally for large files before proxying to Chutes.

## Endpoints

### 1. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "deepseek-ai/DeepSeek-V3.2".
- `stream` (boolean, optional) Default: true.
- `messages` (array, optional) Default: [{"role":"user","content":""}].
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-ai/DeepSeek-V3.2-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": true,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

### 2. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`
- Streaming: yes

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "deepseek-ai/DeepSeek-V3.2".
- `prompt` (string, required)
- `stream` (boolean, optional) Default: true.
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "deepseek-ai/DeepSeek-V3.2-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

### 3. POST /v1/chat/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "deepseek-ai/DeepSeek-V3.2".
- `stream` (boolean, optional) Default: false.
- `messages` (array, optional) Default: [{"role":"user","content":""}].
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-ai/DeepSeek-V3.2-TEE",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7
}'
```

### 4. POST /v1/completions

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:

- `seed` (integer, optional) Default: 42.
- `model` (string, optional) Default: "deepseek-ai/DeepSeek-V3.2".
- `prompt` (string, required)
- `stream` (boolean, optional) Default: false.
- `max_tokens` (integer, optional) Default: 1024.
- `temperature` (number, optional) Default: 0.7.

Example call:

```bash
curl -X POST "https://llm.chutes.ai/v1/completions" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "seed": 42,
  "model": "deepseek-ai/DeepSeek-V3.2-TEE",
  "prompt": "a serene mountain lake at sunset",
  "stream": false,
  "max_tokens": 1024,
  "temperature": 0.7,
  "min_p": 0,
  "top_k": -1,
  "top_p": 1,
  "logprobs": false,
  "ignore_eos": false,
  "min_tokens": 0,
  "top_logprobs": 0,
  "length_penalty": 1,
  "use_beam_search": false,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "repetition_penalty": 1,
  "skip_special_tokens": true,
  "include_stop_str_in_output": false,
  "spaces_between_special_tokens": true
}'
```

### 5. GET /v1/models

- Base URL: `https://llm.chutes.ai`
- Output content type: `application/json`

Request fields:


Example call:

```bash
curl -X GET "https://llm.chutes.ai/v1/models" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```

## Model Facts

- Parameters: 685B total (safetensors weight count)
- Architecture: Mixture-of-Experts transformer with DeepSeek Sparse Attention (DSA); 61 layers, 256 routed experts plus 1 shared, 8 experts active per token
- Context length: 163,840 tokens
- Modalities: text in → text out
- Precision: FP8 (e4m3 block-quantized upstream weights), served in a TEE on Chutes
- License: MIT
- Released: 2025-12
- Experts: 256 routed + 1 shared, 8 active per token
- Layers: 61
- Hidden size: 7168
- Attention heads: 128
- Sparse attention top-k: 2048 tokens indexed per query (index_topk)
- Vocabulary: 129,280 tokens
- Base model: deepseek-ai/DeepSeek-V3.2-Exp-Base (finetune)
- Hugging Face: https://huggingface.co/deepseek-ai/DeepSeek-V3.2

## Recommended Parameters

- `temperature`: 1.0 (model-card recommendation for local deployment; also the generation_config default)
- `top_p`: 0.95 (model-card recommendation; matches generation_config)

## Best For

- Agentic tool-use loops with interleaved reasoning (the chat template supports thinking with tools)
- Long-context tasks where sparse attention keeps cost down at 100K+ token inputs
- Competition-grade math and code reasoning (the model card reports gold-medal results at IMO 2025 and IOI 2025)
- Complex multi-step problem solving where an RL-post-trained reasoner outperforms plain instruct models
- Search-agent pipelines, via the dedicated developer role in the chat template

Not ideal for:

- Vision or audio input: text-only model
- Latency-critical short completions where a smaller dense model is cheaper and faster
- Applications that require the high-compute Speciale variant's tool calling: Speciale is reasoning-only and is a different chute anyway

## FAQ

### What context window does DeepSeek-V3.2 support?

163,840 tokens (max_position_embeddings in the upstream config). DeepSeek Sparse Attention is specifically designed to keep long-context inference efficient, so the model remains practical near the top of that window.

### Does DeepSeek-V3.2 support function calling and tool use?

Yes. This generation introduces a revised tool-calling format and a thinking-with-tools mode in its chat template, and the model was post-trained on large-scale synthesized agentic tasks. Send OpenAI-style tools in your chat completion request via the gateway.

### Can I use DeepSeek-V3.2 commercially?

Yes. Both the repository and the model weights are released under the MIT license, which permits commercial use, modification, and redistribution.

### What does the TEE suffix mean?

The chute runs inference inside a Trusted Execution Environment, i.e. attested confidential-compute hardware. Prompts and outputs are processed inside the enclave. It is a serving-level property and does not change the model's behavior or output quality.

### How do I call it from the OpenAI SDK?

Point the client at base_url https://llm.chutes.ai/v1 with your Chutes API key, and set model to deepseek-ai/DeepSeek-V3.2-TEE. Both chat completions and legacy completions work, and streaming is supported.

### What sampling settings should I use?

DeepSeek recommends temperature 1.0 and top_p 0.95, which also match the repo's generation_config. The chute default is temperature 0.7, so pass the recommended values explicitly if you want reference behavior.

### Is DeepSeek-V3.2 a reasoning model?

Yes, it is post-trained with reinforcement learning for reasoning and emits thinking content via its chat template. DeepSeek reports performance comparable to GPT-5, with the separate high-compute Speciale variant going further on pure reasoning (but without tool calling).


## Model Guide & Sources

- Full model guide: https://chutes.ai/docs/models/chutes-deepseek-ai-deepseek-v3-2-tee
- Source: https://huggingface.co/deepseek-ai/DeepSeek-V3.2
- Source: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/raw/main/config.json
- Source: https://huggingface.co/deepseek-ai/DeepSeek-V3.2/raw/main/generation_config.json
- Source: https://chutes.ai/app/chute/chutes-deepseek-ai-deepseek-v3-2-tee/llms.txt

## Agent Integration Checklist

- Pick the endpoint path that matches the desired task.
- Set `CHUTES_API_KEY` in the server-side environment only.
- Validate required fields before sending requests.
- For media models, keep file upload, base64 conversion, and output preview/download handling explicit in the app UI.