Z.ai · Efficient
GLM-4 Long
Extended context model supporting up to 1M tokens
- Input
- Text
- Output
- Text
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.20
- Output
- $0.20
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- 4.1K
- Average output (7 days)
- 252 tokens
- Longer than 26% of 468 models
Side by side
GLM-4 Long compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM-4 LongZ.aiThis model | DeepSeek V4 Flash Vision ExpDeepSeekRemove | |
|---|---|---|
| Provider | Z.ai | DeepSeek |
| Discovery tier | Efficient | Efficient |
| Added | Jan 1, 2024 | Aug 21, 2026 |
| Limits | ||
| Context window | 1M | 1.05MBest |
| Max output | 4.1K | 384KBest |
| Average output | 252 tokens | 1.3K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.20Best | $0.22 |
| Output | $0.20Best | $0.65 |
| Cache read | — | $0.0069 |
| Performance | ||
| Throughput | — | 123.6 tok/s |
| Time to first token | — | 3.6 s |
| Request success (24h) | — | 99.7% |
| Benchmark indexes | ||
| Intelligence Index | — | 34.3 |
| Coding Index | — | 69.1 |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | No | Yes |
| Vision | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | none, low, high, max |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- GLM-4 Long
- DeepSeek V4 Flash Vision Exp
Intelligence Index
- GLM-4 Long—
- DeepSeek V4 Flash Vision Exp34.3
Indexes
Coding Index
Composite of the coding evaluations
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 69.1
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 54.0%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 23.0%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 1,257 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 1,433 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 11.0%
AA-LCRv1.1
Reasoning across long documents
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 79.7%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 38.6%
GPQA Diamond
Graduate-level science questions
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 90.8%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 12.1%
SciCode
Scientific computing in Python
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 50.3%
Legacy evaluations
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM-4 Long: —
- DeepSeek V4 Flash Vision Exp: 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-4-long",
"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-4-long",
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.