Model comparison
GLM-4.5V vs Kimi-VL-A3B-Thinking-2506
- Input
- $0.60 / 1M tokens
- Output
- $1.80 / 1M tokens
- Context
- 64K
- Released
- 2025-08-11
- Input
- $0.025 / 1M tokens
- Output
- $0.10 / 1M tokens
- Context
- 128K
- Released
- 2025-06-21
GLM-4.5V scores higher on 3 of the 3 benchmarks both models report; Kimi-VL-A3B-Thinking-2506 is cheaper on input tokens ($0 vs $0.6 per 1M, 24×); Kimi-VL-A3B-Thinking-2506 has the larger context window (128K vs 64K).
Specs and pricing side by side
| Spec | GLM-4.5V | Kimi-VL-A3B-Thinking-2506 |
|---|---|---|
| Maker | Z.ai (Zhipu / GLM) | Moonshot AI (Kimi) |
| Released | 2025-08-11 | 2025-06-21 |
| Context window | 64K | 128K |
| Max output | 16K | 32K |
| Input price | $0.60 / 1M tokens | $0.025 / 1M tokens |
| Output price | $1.80 / 1M tokens | $0.10 / 1M tokens |
| Parameters | 106B total / 12B active (MoE) | 16B total / 2.8B active (MoE) |
| License | MIT | MITsame |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision, Video, PDF | Text, Vision, Video, PDFsame |
| Knowledge cutoff | December 2024 | December 2024same |
Benchmarks both models report
| Benchmark | GLM-4.5V | Kimi-VL-A3B-Thinking-2506 |
|---|---|---|
| MMStar | 75.3% | 70.4% |
| MMMU Pro | 65.2% | 46.3% |
| MathVista | 84.6% | 80.1% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick GLM-4.5V if…
- You care about MMStar, MMMU Pro, MathVista (it scores higher on 3 shared benchmarks).
- Your use case is: document, chart and long-PDF understanding and information extraction.
Pick Kimi-VL-A3B-Thinking-2506 if…
- Cost matters: input tokens cost 24× less ($0 vs $0.6 per 1M).
- You need the longer context (128K vs 64K).
- Your use case is: visual and multimodal math/reasoning over charts, diagrams and screenshots.
FAQ
Which is better, GLM-4.5V or Kimi-VL-A3B-Thinking-2506?
GLM-4.5V scores higher on 3 of the 3 benchmarks both models report; Kimi-VL-A3B-Thinking-2506 is cheaper on input tokens ($0 vs $0.6 per 1M, 24×); Kimi-VL-A3B-Thinking-2506 has the larger context window (128K vs 64K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Kimi-VL-A3B-Thinking-2506?
GLM-4.5V: $0.60 / 1M tokens input, $1.80 / 1M tokens output. Kimi-VL-A3B-Thinking-2506: $0.025 / 1M tokens input, $0.10 / 1M tokens output (list API prices as published by each maker).
What are the context windows of GLM-4.5V and Kimi-VL-A3B-Thinking-2506?
GLM-4.5V offers 64K with up to 16K output; Kimi-VL-A3B-Thinking-2506 offers 128K with up to 32K output.
Is GLM-4.5V newer than Kimi-VL-A3B-Thinking-2506?
GLM-4.5V was released 2025-08-11; Kimi-VL-A3B-Thinking-2506 was released 2025-06-21.
Go deeper
- GLM-4.5V: full specs, pricing and benchmarks
- Kimi-VL-A3B-Thinking-2506: full specs, pricing and benchmarks
- glm 4 6v vs glm 4 5v
- glm 4 5v vs glm 4 1v thinking
- kimi vl a3b thinking 2506 vs qwen2 5 vl
- qwen3 vl vs kimi vl a3b thinking 2506
- glm 4 1v thinking vs kimi vl a3b thinking 2506
- qwen3 vl vs glm 4 5v
- All model comparisons