deepseek-ai/DeepSeek-V3.2-TEE — Chutes API
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.
- Model name: deepseek-ai/DeepSeek-V3.2-TEE
- Chute ID: 398651e1-5f85-5e50-a513-7c5324e8e839
- Base URL: https://llm.chutes.ai/v1
- Authentication: Authorization: Bearer $CHUTES_API_KEY
- OpenAI-compatible — set the request "model" field to deepseek-ai/DeepSeek-V3.2-TEE
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)
Full model guide: /docs/models/chutes-deepseek-ai-deepseek-v3-2-tee
Full machine-readable API references: llms.txt (agent guide), openapi.json (OpenAPI 3.1), docs.
