GLM-5.1

Z.ai (Zhipu AI)balanced NewOpen Source

Z.ai's (Zhipu) 2026 flagship. 200K context, strong agentic and tool-use scores — 98% on τ²-Bench Telecom, on par with Grok 4.3. Artificial Analysis Intelligence Index 51.

Context Window

200K

tokens

Max Output

16K

tokens

Input Price

$1.55

per 1M tokens

Output Price

$4.65

per 1M tokens

Speed

48

tokens/sec

Released

Apr 2026

2026-04-28

Blended Cost

$3.10

per 1M tokens

Value Score

28.4

quality per $

Capabilities

ChatVisionFunction CallingCode GenerationReasoning

Benchmarks

Quality Index
88
MMLU Pro
85.8
HumanEval (Coding)
88.6
MATH
83.4
Arena ELO
1467

Open Source — Licensed under MIT

About GLM-5.1

GLM-5.1 is a balanced AI model by Z.ai (Zhipu AI), released on April 28, 2026. It supports a context window of 200K tokens and can generate up to 16K output tokens.

At $1.55 per million input tokens and $4.65 per million output tokens, its blended cost of $3.10/1M tokens puts it in the mid-range pricing tier. Its value score of 28.4 reflects the balance of quality and cost.

GLM-5.1 is available as an open-source model under the MIT license, meaning you can self-host it for predictable costs or use it through API providers like Swfte Connect.

Using GLM-5.1 with Swfte

Access GLM-5.1 through Swfte Connect, our unified LLM gateway. Connect gives you a single API for 50+ models, with automatic routing, cost optimization, and fallback handling. You can also try GLM-5.1 in our AI Playground before integrating.