Sign in to use the playground
Run this model with your Chutes account, quota, and API access.
Model facts & API quick start
Qwen3-32B (Qwen/Qwen3-32B-TEE) is served on Chutes inside a Trusted Execution Environment (TEE). Call it through the OpenAI-compatible API at https://llm.chutes.ai/v1 with a Chutes API key and "model": "Qwen/Qwen3-32B-TEE".
Qwen3-32B at a glance
- Model ID
Qwen/Qwen3-32B-TEE- Developer
- Qwen
- Deployed by
- chutes
- Type
- LLM
- Input price
- $0.104 per 1M tokens
- Output price
- $0.416 per 1M tokens
- Cached input price
- $0.0104 per 1M tokens
- Context length
- 40,960 tokens
- Modalities
- text in → text out
- Confidential compute (TEE)
- Yes, runs in a Trusted Execution Environment
- Precision
- FP8 (as served on Chutes)
- Open weights
Qwen/Qwen3-32B-FP8- Parameters
- 32.8B (31.2B non-embedding)
- Architecture
- Dense causal transformer (Qwen3ForCausalLM), 64 layers, GQA with 64 query heads and 8 KV heads
- License
- Apache-2.0
- Released
- 2025-04
- Native context
- 32,768 tokens; validated up to 131,072 with YaRN (model card)
- Thinking modes
- Hybrid: thinking mode on by default, hard switch via enable_thinking, soft switch via /think and /no_think
- Vocabulary
- 151,936 tokens
- RoPE theta
- 1,000,000
- Serving on Chutes
- TEE, FP8 weights, DFLASH speculative decoding
API quick start
- Base URL
https://llm.chutes.ai/v1- model
Qwen/Qwen3-32B-TEE- Endpoint
POST /v1/chat/completions- Auth header
Authorization: Bearer $CHUTES_API_KEY
OpenAI-compatible: point any OpenAI SDK at the base URL above and pass your Chutes API key as the API key.
curl -X POST "https://llm.chutes.ai/v1/chat/completions" \
-H "Authorization: Bearer $CHUTES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Qwen/Qwen3-32B-TEE",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true,
"max_tokens": 1024,
"temperature": 0.7
}'Qwen3-32B FAQ
What context window does Qwen3-32B support on Chutes?
The upstream model natively handles 32,768 tokens and its config sets max_position_embeddings to 40,960. The model card documents up to 131,072 tokens only when YaRN RoPE scaling is enabled by the serving stack, so plan around the native window unless you have verified longer prompts against the live endpoint.
Does Qwen3-32B think before answering?
Yes, by default. Qwen3 is a hybrid-reasoning model: thinking mode emits reasoning wrapped in <think> tags before the final answer. You can disable it with the enable_thinking template switch or per turn with /no_think in the prompt, which trades reasoning depth for speed and fewer output tokens.
What sampling settings should I use?
The Qwen team recommends temperature 0.6, top_p 0.95, top_k 20, min_p 0 for thinking mode (these match generation_config.json) and temperature 0.7, top_p 0.8, top_k 20 for non-thinking mode. They explicitly warn against greedy decoding in thinking mode because it can cause repetition loops.
Can I use it with the OpenAI SDK?
Yes. Point the SDK at base_url https://llm.chutes.ai/v1 with your Chutes API key and set model to Qwen/Qwen3-32B-TEE. Standard chat.completions calls, streaming included, work unchanged.
What does the TEE suffix mean?
The model runs inside a Trusted Execution Environment: confidential-compute hardware that keeps prompts and outputs encrypted in memory and attestable. It is a deployment property of this chute, not a different model; the weights are Qwen/Qwen3-32B served in FP8.
Does FP8 or speculative decoding change the model's outputs?
FP8 is a weight/activation precision used for serving efficiency and DFLASH speculative decoding accelerates generation; the model card facts (architecture, training) are unchanged. Speculative decoding is lossless with respect to the target model's distribution, while FP8 quantization can introduce small numerical differences versus BF16.
Is Qwen3-32B free for commercial use?
Yes. The upstream repository is licensed Apache-2.0, which permits commercial use, modification, and redistribution with attribution. Your usage of the Chutes endpoint is billed per Chutes pricing, which is separate from the model license.
Does it support function calling and tools?
Yes. The model card highlights agent and tool-calling capability and recommends the Qwen-Agent framework, which bundles Qwen3's tool-call templates and parsers. Through the OpenAI-compatible endpoint you can also drive tool use with standard tools/tool_choice request fields where supported.