# Qwen/Qwen3.5-397B-A17B-TEE

> Qwen/Qwen3.5-397B-A17B-FP8

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-qwen-qwen3-5-397b-a17b-tee
- Model llms.txt: https://chutes.ai/app/chute/chutes-qwen-qwen3-5-397b-a17b-tee/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/chutes-qwen-qwen3-5-397b-a17b-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: `Qwen/Qwen3.5-397B-A17B-TEE`
- Chute ID: `51a4284a-a5a0-5e44-a9cc-6af5a2abfbcf`
- Slug: `chutes-qwen-qwen3-5-397b-a17b-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 (`Qwen/Qwen3.5-397B-A17B-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: "Qwen/Qwen3.5-397B-A17B-FP8".
- `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": "Qwen/Qwen3.5-397B-A17B-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: "Qwen/Qwen3.5-397B-A17B-FP8".
- `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": "Qwen/Qwen3.5-397B-A17B-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: "Qwen/Qwen3.5-397B-A17B-FP8".
- `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": "Qwen/Qwen3.5-397B-A17B-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: "Qwen/Qwen3.5-397B-A17B-FP8".
- `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": "Qwen/Qwen3.5-397B-A17B-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: 397B total
- Active parameters: 17B per token
- Architecture: Hybrid vision-language MoE: Gated DeltaNet linear attention interleaved with gated attention (layout 15 x (3 x (Gated DeltaNet -> MoE) -> 1 x (Gated Attention -> MoE))), 512 experts, plus a vision encoder with early-fusion multimodal training
- Context length: 262,144 tokens
- Modalities: text, image, video in → text out
- Precision: FP8 (as served on Chutes; upstream weights BF16)
- License: Apache-2.0
- Released: 2026-02
- Experts: 512 total; 10 routed + 1 shared activated per token
- Layers / hidden size: 60 / 4096
- Context extension: 262,144 native, extensible up to 1,010,000 tokens
- Languages: 201 languages and dialects
- Vocabulary: 248,320 tokens (padded)
- Hugging Face: https://huggingface.co/Qwen/Qwen3.5-397B-A17B

## Recommended Parameters

- `temperature`: 0.6 (generation_config.json default; model card recommendation for thinking mode (0.7 for non-thinking))
- `top_p`: 0.95 (generation_config.json default; thinking mode (0.8 for non-thinking))
- `top_k`: 20 (generation_config.json default and model card recommendation)
- `presence_penalty`: 0-2 (card suggests raising to reduce endless repetition; high values can cause language mixing)
- `max_tokens`: 32768 (card-recommended output length for most queries; 81,920 for competition-grade math and coding)

## Best For

- Multimodal reasoning: images and documents in the same conversation as text
- Agentic workflows: RL-trained across million-agent environments for tool-use robustness
- Multilingual products: 201 languages and dialects
- Long-context tasks with 262K native window
- High-throughput serving: only 17B of 397B parameters activate per token, with linear-attention efficiency at long context

Not ideal for:

- Audio input or speech output: vision-language only
- Image generation: it consumes images but only emits text
- Bit-exact reproduction of full-precision outputs: this chute serves the FP8 build

## FAQ

### What does 397B-A17B mean?

397B total parameters with 17B activated per token. It is a sparse Mixture-of-Experts model: each MoE layer holds 512 experts but routes each token through only 10 routed plus 1 shared expert, so you get large-model quality at a fraction of the per-token compute.

### Can it process images?

Yes. Qwen3.5 is a unified vision-language model with a vision encoder trained by early fusion, and its card reports results on visual reasoning and video benchmarks. Send OpenAI-style multimodal content parts (image_url) in your chat messages.

### What context window does it support?

262,144 tokens natively, extensible up to 1,010,000 per the model card. The chute's default max_tokens is 1,024; the card recommends 32,768-token outputs for most queries and up to 81,920 for hard math and coding.

### What sampling settings should I use?

For thinking mode: temperature 0.6, top_p 0.95, top_k 20, min_p 0 (also the generation_config.json defaults). For non-thinking mode: temperature 0.7, top_p 0.8, top_k 20. presence_penalty between 0 and 2 reduces endless repetition, at some risk of language mixing.

### Can I use it commercially?

Yes. The model is released under the Apache-2.0 license, which permits commercial use, modification, and redistribution.

### What does the TEE suffix mean?

TEE stands for Trusted Execution Environment. Inference runs inside attested confidential-compute hardware, so your prompts and the model's outputs are processed within a hardware-isolated enclave rather than on an open host.

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

Set base_url to https://llm.chutes.ai/v1 with your Chutes API key and model to Qwen/Qwen3.5-397B-A17B-TEE. Chat completions, raw completions, and streaming work through the standard SDK methods.

### Should I keep thinking content in multi-turn history?

No. The model card's best practices say historical turns should contain only the final output, not the thinking content. The official chat template handles this automatically; if you manage history yourself, strip reasoning blocks before resending.


## Model Guide & Sources

- Full model guide: https://chutes.ai/docs/models/chutes-qwen-qwen3-5-397b-a17b-tee
- Source: https://huggingface.co/Qwen/Qwen3.5-397B-A17B
- Source: https://huggingface.co/Qwen/Qwen3.5-397B-A17B-FP8
- Source: https://chutes.ai/app/chute/chutes-qwen-qwen3-5-397b-a17b-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.