GLM-5.1 Non-reasoning NEW
Z.ai's chat-tier counterpart
GLM-5.1 in non-reasoning mode — same 744B/40B-active MoE backbone as the reasoning sibling but answers directly without an explicit chain-of-thought. Lower latency, ~7 AA Intel points lower on hardest benchmarks. MIT licensed at $1.40/$4.40 hosted.
Intelligence
Good
Speed
Slow
53 tok/s output
Cost
Moderate
$1.40 in / $4.40 out
Context
200K
Up to 200,000 tokens
How are Intelligence, Speed & Cost bucketed?
Intelligence and Speed buckets are percentile ranks on
Artificial Analysis. Cost buckets are fixed dollar
thresholds keyed off output-token price ($/M out).
Intelligence
- Top 1%≤ 1%
- Top 5%≤ 5%
- Top 10%≤ 10%
- Good≤ 25%
- Medium≤ 50%
- Below avg> 50%
Speed
- Top 1%≥ 345 tok/s
- Top 5%≥ 237 tok/s
- Top 10%≥ 196 tok/s
- Good≥ 146 tok/s
- Medium≥ 90 tok/s
- Slow< 90 tok/s
Cost
- Freeopen weights · self-host
- Low< $1 / M out
- Moderate$1–5 / M out
- High≥ $5 / M out
Why it matters
Demonstrates the "one weight set, two modes" pattern in the open-weights tier. Lowers the barrier to running both reasoning and chat modes from a single self-hosted deployment.
Core Capabilities
Long Documents
Handles entire codebases, books, and multi-doc RAG.
Generative
Produces images, video, audio, or other media.
Context Window
200k tokens
≈ 154+ pages
4k Chat 聊天
32k Long docs 长文档
128k Books 整本书
400k Multi-doc 多文档
1M Codebase 整个代码库
10M
200k
Availability
API
Available
Product / App
Not available
Open Source
Released
Enterprise
Contact sales
Pricing Model
Free / self-host
Open weights — pay only for compute.
Self-host Capability / Performance
Where this model sits relative to the middle 60% of models in the tree. All scores are 0–10 (higher is better).
Lower 20% Upper 80% This model
Context / memory
Context window size · log-scaled
6.0
9.0
6.7
Lower 20% 20th percentile — 20% of models score below this This model Where the current model lands Upper 80% 80th percentile — only 20% of models score above this
Percentile boundaries are computed across every model in the tree that reports the underlying benchmark for each capability.
What it feels like
- Direct chat-style answers without explicit reasoning traces — lower latency than the reasoning sibling
- Still solid frontier-class on knowledge (GPQA 83.9%, MMLU-Pro), but ~7 AA Intel points behind the reasoning mode
Best use cases
- Chat / customer support / writing where you want speed over chain-of-thought
- Workloads where reasoning traces would be wasteful (translation, classification, summarisation)
- Self-host with the same weights as GLM-5.1 Reasoning — switch modes via prompting
Tools to try
Not ideal for
- Hardest math / coding tasks — switch to GLM-5.1 Reasoning for those
- Multimodal / vision — text-only
Model Evolution
GLM is Zhipu's language model family.