Z.ai · Balanced
GLM Z1 AirX
Fastest reasoning model in China, with up to 200 tokens per second. The stronger version of GLM Z1 Air.
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Balanced
Pricing
USD per 1M tokens- Input
- $0.70
- Output
- $0.70
Reference prices as published by the model provider. API example
Specifications
- Context window
- 32K
- Max output
- 16.4K
Side by side
GLM Z1 AirX compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM Z1 AirXZ.aiThis model | GLM 5.3 TEEZ.aiRemove | |
|---|---|---|
| Provider | Z.ai | Z.ai |
| Discovery tier | Balanced | Open weights |
| Added | Apr 15, 2025 | Aug 31, 2026 |
| Limits | ||
| Context window | 32K | 1.05MBest |
| Max output | 16.38K | 131.07KBest |
| Average output | — | 1.2K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.70Best | $1.40 |
| Output | $0.70Best | $4.40 |
| Cache read | — | $0.26 |
| Performance | ||
| Throughput | — | 36.9 tok/s |
| Time to first token | — | 4.6 s |
| Request success (24h) | — | 99.7% |
| Benchmark indexes | ||
| Intelligence Index | — | 44.8 |
| Coding Index | — | 74.8 |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Parallel tools | No | Yes |
| Reasoning effort | — | low, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM Z1 AirX
- GLM 5.3 TEE
Intelligence Index
- GLM Z1 AirX—
- GLM 5.3 TEE44.8
Indexes
Coding Index
Composite of the coding evaluations
- GLM Z1 AirX: —
- GLM 5.3 TEE: 74.8
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GLM Z1 AirX: —
- GLM 5.3 TEE: 62.2%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GLM Z1 AirX: —
- GLM 5.3 TEE: 29.4%
Harvey LAB-AAv1.1
Legal tasks passed in full, with no material hallucination
- GLM Z1 AirX: —
- GLM 5.3 TEE: 0.3%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GLM Z1 AirX: —
- GLM 5.3 TEE: 1,505 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM Z1 AirX: —
- GLM 5.3 TEE: 1,649 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GLM Z1 AirX: —
- GLM 5.3 TEE: 11.2%
AA-LCRv1.1
Reasoning across long documents
- GLM Z1 AirX: —
- GLM 5.3 TEE: 79.7%
MLCR-AA
Long-context reasoning over medical records
- GLM Z1 AirX: —
- GLM 5.3 TEE: 17.2%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM Z1 AirX: —
- GLM 5.3 TEE: 42.3%
GPQA Diamond
Graduate-level science questions
- GLM Z1 AirX: —
- GLM 5.3 TEE: 91.7%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GLM Z1 AirX: —
- GLM 5.3 TEE: 41.9%
SciCode
Scientific computing in Python
- GLM Z1 AirX: —
- GLM 5.3 TEE: 59.0%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM Z1 AirX: —
- GLM 5.3 TEE: 79.7%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-z1-airx",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="glm-z1-airx",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Z.ai
Related models
Other Z.ai models, starting with the same family.