Model comparison
GLM-4.1V-9B-Thinking vs Kimi-VL-A3B-Thinking-2506
- Input
- $0.035 / 1M tokens
- Output
- $0.14 / 1M tokens
- Context
- 64K
- Released
- 2025-07-01
- Input
- $0.025 / 1M tokens
- Output
- $0.10 / 1M tokens
- Context
- 128K
- Released
- 2025-06-21
GLM-4.1V-9B-Thinking scores higher on 4 of the 4 benchmarks both models report; Kimi-VL-A3B-Thinking-2506 is cheaper on input tokens ($0 vs $0 per 1M, 1.4×); Kimi-VL-A3B-Thinking-2506 has the larger context window (128K vs 64K).
Specs and pricing side by side
| Spec | GLM-4.1V-9B-Thinking | Kimi-VL-A3B-Thinking-2506 |
|---|---|---|
| Maker | Z.ai (Zhipu / GLM) | Moonshot AI (Kimi) |
| Released | 2025-07-01 | 2025-06-21 |
| Context window | 64K | 128K |
| Max output | 8K | 32K |
| Input price | $0.035 / 1M tokens | $0.025 / 1M tokens |
| Output price | $0.14 / 1M tokens | $0.10 / 1M tokens |
| Parameters | 9B | 16B total / 2.8B active (MoE) |
| License | MIT | MITsame |
| Weights | Open weights | Open weightssame |
| Modalities | Text, Vision, Video | Text, Vision, Video, PDF |
| Knowledge cutoff | Not disclosed | December 2024 |
Benchmarks both models report
| Benchmark | GLM-4.1V-9B-Thinking | Kimi-VL-A3B-Thinking-2506 |
|---|---|---|
| MMStar | 72.9% | 70.4% |
| MathVista | 80.7% | 80.1% |
| MMMU | 68% | 64% |
| MMMU-Pro | 57.1% | 46.3% |
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-4.1V-9B-Thinking if…
- You care about MMStar, MathVista, MMMU (it scores higher on 4 shared benchmarks).
- Your use case is: solving STEM and math problems presented as images, diagrams, or charts.
Pick Kimi-VL-A3B-Thinking-2506 if…
- Cost matters: input tokens cost 1.4× less ($0 vs $0 per 1M).
- You need the longer context (128K vs 64K).
- You need PDF input, which GLM-4.1V-9B-Thinking lacks.
- Your use case is: visual and multimodal math/reasoning over charts, diagrams and screenshots.
FAQ
Which is better, GLM-4.1V-9B-Thinking or Kimi-VL-A3B-Thinking-2506?
GLM-4.1V-9B-Thinking scores higher on 4 of the 4 benchmarks both models report; Kimi-VL-A3B-Thinking-2506 is cheaper on input tokens ($0 vs $0 per 1M, 1.4×); 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-4.1V-9B-Thinking: $0.035 / 1M tokens input, $0.14 / 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-4.1V-9B-Thinking and Kimi-VL-A3B-Thinking-2506?
GLM-4.1V-9B-Thinking offers 64K with up to 8K output; Kimi-VL-A3B-Thinking-2506 offers 128K with up to 32K output.
Is GLM-4.1V-9B-Thinking newer than Kimi-VL-A3B-Thinking-2506?
GLM-4.1V-9B-Thinking was released 2025-07-01; Kimi-VL-A3B-Thinking-2506 was released 2025-06-21.
Go deeper
- GLM-4.1V-9B-Thinking: full specs, pricing and benchmarks
- Kimi-VL-A3B-Thinking-2506: full specs, pricing and benchmarks
- 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 qwen2 5 omni
- glm 4 5v vs kimi vl a3b thinking 2506
- All model comparisons