Z.ai · Open weights
GLM 4.6V Original
GLM-4.6V scales its context window to 128k tokens in training, and achieves SoTA performance in visual understanding among models of similar parameter scales. Integrates native Function Calling capabilities, bridging 'visual perception' and 'executable action' for multimodal agents. Direct via Z-AI (Zhipu).
- Vision
- Input
- Text, Images
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.60
- Output
- $0.90
Reference prices as published by the model provider. API example
Specifications
- Context window
- 128K
- Max output
- 24K
- Average output (7 days)
- 258 tokens
- Longer than 27% of 468 models
Side by side
GLM 4.6V Original compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| GLM 4.6V OriginalZ.aiThis model | Apex Flash 1Z.aiRemove | |
|---|---|---|
| Provider | Z.ai | Z.ai |
| Discovery tier | Open weights | Open weights |
| Added | Dec 8, 2025 | Oct 5, 2026 |
| Limits | ||
| Context window | 128K | 1.05MBest |
| Max output | 24K | 32.77KBest |
| Average output | 258 tokens | 672 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.60 | $0.15Best |
| Output | $0.90 | $0.50Best |
| Cache read | — | $0.075 |
| Performance | ||
| Throughput | — | 14.1 tok/s |
| Time to first token | — | 6.9 s |
| Request success (24h) | — | 94.6% |
| Benchmark indexes | ||
| Intelligence Index | 8.4 | — |
| Math Index | 26.3 | — |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | No | Yes |
| Vision | Yes | 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 4.6V Original
- Apex Flash 1
Intelligence Index
- GLM 4.6V Original8.4
- Apex Flash 1—
GLM 4.6V Original: Better than 13% of 326 scored models
Indexes
Math Index
Composite of the math evaluations
- GLM 4.6V Original: 26.3
- Apex Flash 1: —
Document reasoning
AA-LCRv1.1
Reasoning across long documents
- GLM 4.6V Original: 17.0%
- Apex Flash 1: —
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- GLM 4.6V Original: 3.7%
- Apex Flash 1: —
GPQA Diamond
Graduate-level science questions
- GLM 4.6V Original: 56.6%
- Apex Flash 1: —
MMLU-Pro
Multi-subject knowledge and reasoning
- GLM 4.6V Original: 75.2%
- Apex Flash 1: —
IFBench
Following precise output instructions
- GLM 4.6V Original: 27.9%
- Apex Flash 1: —
Coding
LiveCodeBench
Recent competitive programming problems
- GLM 4.6V Original: 41.1%
- Apex Flash 1: —
Math
AIME 2025
Competition mathematics, 2025 problems
- GLM 4.6V Original: 26.3%
- Apex Flash 1: —
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- GLM 4.6V Original: 3.0%
- Apex Flash 1: —
τ²-Bench Telecom
Tool use in a customer-support simulation
- GLM 4.6V Original: 30.7%
- Apex Flash 1: —
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- GLM 4.6V Original: 17.0%
- Apex Flash 1: —
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": "z-ai/glm-4.6v-original",
"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="z-ai/glm-4.6v-original",
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.