Sign in to use the playground
Run this model with your Chutes account, quota, and API access.
Model facts & API quick start
GLM-5.1 (zai-org/GLM-5.1-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": "zai-org/GLM-5.1-TEE".
GLM-5.1 at a glance
- Model ID
zai-org/GLM-5.1-TEE- Developer
- Z.AI
- Deployed by
- chutes
- Type
- LLM
- Input price
- $0.98 per 1M tokens
- Output price
- $3.08 per 1M tokens
- Cached input price
- $0.098 per 1M tokens
- Context length
- 202,752 tokens
- Modalities
- text in → text out
- Confidential compute (TEE)
- Yes, runs in a Trusted Execution Environment
- Precision
- FP8 (as served on Chutes; upstream weights BF16)
- Open weights
zai-org/GLM-5.1-FP8- Parameters
- 754B total (safetensors count; same architecture and size as GLM-5, listed as 744B on the GLM-5 card)
- Active parameters
- 40B per token (identical configuration to GLM-5)
- Architecture
- Mixture-of-Experts transformer with DeepSeek Sparse Attention (DSA); 78 layers, 256 routed + 1 shared experts, 8 routed experts per token
- License
- MIT
- Released
- 2026-04
- Experts
- 256 routed + 1 shared, 8 routed active per token
- Layers / hidden size
- 78 / 6144
- SWE-Bench Pro
- 58.4 (model card; state-of-the-art at release)
- Terminal-Bench 2.0 (Terminus-2)
- 63.5 (model card)
- CyberGym
- 68.7 (model card)
API quick start
- Base URL
https://llm.chutes.ai/v1- model
zai-org/GLM-5.1-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": "zai-org/GLM-5.1-TEE",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"stream": true,
"max_tokens": 1024,
"temperature": 0.7
}'GLM-5.1 FAQ
How is GLM-5.1 different from GLM-5?
Same architecture and size, retrained for agentic engineering. It reaches 58.4 on SWE-Bench Pro (state-of-the-art at release) and improves sharply on NL2Repo (42.7 vs 35.9) and Terminal-Bench 2.0 (63.5 vs 56.2). Most importantly, it stays productive over much longer autonomous sessions instead of plateauing early.
What context window does GLM-5.1 support?
The config.json sets max_position_embeddings to 202,752 tokens, roughly 200K. The chute's default max_tokens is 1,024, so raise it for long outputs.
Does GLM-5.1 support function calling and tool use?
Yes. Long-horizon tool use is the model's design focus: Z.ai reports it sustaining thousands of tool calls per session, and it scores 71.8 on MCP-Atlas and 40.7 on Tool-Decathlon. Pass OpenAI-style tools in your chat completion request.
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.
Can I use GLM-5.1 commercially?
Yes. GLM-5.1 is released under the MIT license, which permits commercial use, modification, and redistribution.
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 zai-org/GLM-5.1-TEE. Chat completions, raw completions, and streaming work through the standard SDK methods.
What sampling settings should I use?
The upstream generation_config.json defaults to temperature 1.0 and top_p 0.95. The chute's own default temperature is 0.7 with max_tokens 1024; for agent workloads, raise max_tokens well above the default.