Cheaper overall
GLM 4.5V
10% lower blended rate
Higher benchmark scores
GLM 4.5
leads on 9 of 9 figures
Bigger context window
GLM 4.5
128,000 vs 65,536 tokens
Where each one wins
GLM 4.5V
- Cheaper output tokens $1.80 vs $2.20, 18% less
- Cheaper on all four workloads
GLM 4.5
- Larger context window 128,000 tokens
- Longer maximum output 98,304 tokens
- Higher overall intelligence (Intelligence Index) 12.8 vs 7.6
- Higher graduate-level science (GPQA Diamond) 78.2 vs 68.4
- Higher expert-exam performance (Humanity's Last Exam) 13 vs 6.3
- Ahead on 6 more benchmark figures
What four workloads cost
One run, and the same run a thousand times.
GLM 4.5V is cheaper on all four workloads, by much the same margin each time โ about 1.1 times, from $0.0015 against $0.0017 on a chat turn to $0.1152 against $0.1208 on a long document.
| Workload | GLM 4.5V | GLM 4.5 | ร1,000 | Difference |
|---|---|---|---|---|
| Chat turn 1,000 in / 500 out | $0.0015 | $0.0017 | $1.50 / $1.70 | GLM 4.5V is 12% cheaper |
| RAG answer 10,000 in / 800 out | $0.0074 | $0.0078 | $7.44 / $7.76 | GLM 4.5V is 4% cheaper |
| Agent loop 32,000 in / 700 out ร 20 calls | $0.1152 | $0.1208 | $115.20 / $120.80 | GLM 4.5V is 5% cheaper |
| Long document 400,000 in / 3,000 out | GLM 4.5V's context window holds 65,536 tokens, so a 400,000-token prompt does not fit. | |||
Price per 1M tokens
Neither model changes its rate with prompt length, so these rates apply to every request.
| Context band | Price | GLM 4.5V | GLM 4.5 | Difference |
|---|---|---|---|---|
| Any prompt length | Input | $0.60 | $0.60 | Same |
| Any prompt length | Cached input | $0.11 | $0.11 | Same |
| Any prompt length | Output | $1.80 | $2.20 | GLM 4.5V is 18% cheaper |
Blended: GLM 4.5V $0.90, GLM 4.5 $1.00 per 1M โ one rate at 3:1 input to output, for comparing two models at a glance.
Both priced by Z.ai. Standard tier, pay-as-you-go.
Benchmarks
GLM 4.5 leads on all 10 figures, furthest ahead on long-context reasoning (AA-LCR), by 52.7 points.
Overall intelligence
Intelligence Index โ Overall intelligence across reasoning, knowledge & math evals
GLM 4.5 ahead by 5.2
Graduate-level science
GPQA Diamond โ Graduate-level questions in biology, chemistry & physics
GLM 4.5 ahead by 9.8
Expert-exam performance
Humanity's Last Exam โ Expert-level questions across many academic domains
GLM 4.5 ahead by 6.7
Instruction following
IFBench โ Precise following of detailed instructions
GLM 4.5 ahead by 9.9
Support-agent performance
ฯยฒ-Bench Telecom โ Tool-using agent tasks in a telecom support setting
GLM 4.5 ahead by 20.5
Long-context reasoning
AA-LCR โ Long-context reasoning across large inputs
GLM 4.5 ahead by 52.7
Command-line work
Terminal-Bench Hard โ Complex command-line and terminal workflows
GLM 4.5 ahead by 15.2
Physics research reasoning
CritPt โ Unpublished physics research reasoning problems
Level
Factual accuracy
Omniscience Accuracy โ Breadth of factual knowledge across domains
GLM 4.5 ahead by 4.3
Answer reliability
Omniscience Non-Hallucination โ How reliably the model avoids fabricated answers
GLM 4.5 ahead by 14.7
Each figure is that model's best published run, with the effort level named beside it โ where these scores come from.
Specifications
GLM 4.5 holds 62,464 more input tokens in one request. GLM 4.5V also takes image and video. Only GLM 4.5 lists prompt caching.
| Specification | GLM 4.5V | GLM 4.5 |
|---|---|---|
| Context window | 65,536 tokens | 128,000 tokens |
| Max output | 16,384 tokens | 98,304 tokens |
| Takes in | Text, image, video | Text |
| Puts out | Text | Text |
| Knowledge cutoff | 31 Dec 2024 | 31 Dec 2024 |
| Released | 11 Aug 2025 | 26 Jul 2025 |
| Status | Active | Active |
| Sold by | Z.ai | Z.ai |
| Tool use | Yes | Yes |
| Structured outputs | Not listed | Not listed |
| Web search | Not listed | Not listed |
| Prompt caching | Not listed | Yes |
| Code execution | Not listed | Not listed |
| Computer use | Not listed | Not listed |
| Open weights | Yes | Yes |
| Reasoning | Yes | Yes |
FAQs
- Is GLM 4.5V cheaper than GLM 4.5?
- Yes. A 1,000-token prompt with a 500-token reply costs $0.0015 on GLM 4.5V and $0.0017 on GLM 4.5, and the same model is cheaper on every workload on this page.
- How much do GLM 4.5V and GLM 4.5 cost per 1M tokens?
- GLM 4.5V costs $0.60 for input and $1.80 for output. GLM 4.5 costs $0.60 and $2.20. Standard pay-as-you-go rates, as of 11 Aug 2025.
- Which is better, GLM 4.5V or GLM 4.5?
- On published benchmarks, GLM 4.5. It leads on 9 of the 10 figures both models report, including overall intelligence (Intelligence Index), where it scores 12.8 against 7.6.
- Does GLM 4.5V or GLM 4.5 have a bigger context window?
- GLM 4.5, at 128,000 tokens against 65,536. That is 62,464 more input tokens in a single request.