AI model comparison
Qwen3 Next 80B A3B Thinking vs GLM 4.5 Air
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default.
- Input / 1M
- $0.15
- Output / 1M
- $1.20
- Context
- 262K
Z.ai
GLM 4.5 Air
GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications.
- Input / 1M
- $0.13
- Output / 1M
- $0.85
- Context
- 131K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GLM 4.5 Air
1.3x cheaper for a typical chat
Higher intelligence score
Qwen3 Next 80B A3B Thinking
11.2 vs 11.1 on Artificial Analysis
Larger context window
Qwen3 Next 80B A3B Thinking
262K vs 131K tokens
Newer release
Qwen3 Next 80B A3B Thinking
Released September 11, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Qwen3 Next 80B A3B Thinking11.2Coding index
Qwen3 Next 80B A3B Thinking17.4Agentic index
Qwen3 Next 80B A3B ThinkingNot availablePricing
Qwen3 Next 80B A3B Thinking vs GLM 4.5 Air API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Qwen3 Next 80B A3B Thinking | |
|---|---|---|
| Input tokensPer 1M tokens | $0.15 | $0.13 |
| Output tokensPer 1M tokens | $1.20 | $0.85 |
| Cached input (read)Per 1M tokens | Not available | $0.03 |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Qwen3 Next 80B A3B Thinking$0.90Coding task
30K in, 4K out
Qwen3 Next 80B A3B Thinking$9.30Long document summary
150K in, 2K out
Qwen3 Next 80B A3B Thinking$24.90Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Qwen3 Next 80B A3B Thinking | |
|---|---|---|
| Context window | 262K tokens | 131K tokens |
| Max output | 236K tokens | 98K tokens |
| Input types | Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | September 11, 2025 | July 25, 2025 |
Features
Supported features
API features available for each model.
| Metric | Qwen3 Next 80B A3B Thinking | |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Not supported |
| JSON mode | Supported | Not supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Qwen3 Next 80B A3B ThinkingView full model details- Qwen3 Next 80B A3B Thinking vs Qwen3 235B A22B Instruct 2507
- Qwen3 Next 80B A3B Thinking vs Qwen3 Coder 480B A35B
- Qwen3 Next 80B A3B Thinking vs GLM 4.6V
- Qwen3 Next 80B A3B Thinking vs GPT-4.1 Mini
- Qwen3 Next 80B A3B Thinking vs Qwen3 VL 235B A22B Instruct
- Qwen3 Next 80B A3B Thinking vs DeepSeek V3 0324
- Qwen3 Next 80B A3B Thinking vs Qwen3 Next 80B A3B Instruct
- Qwen3 Next 80B A3B Thinking vs Qwen3 VL 30B A3B Thinking
- Qwen3 Next 80B A3B Thinking vs Qwen3 Coder Next
- GLM 4.5 Air vs Gemini 2.5 Flash Lite
- GLM 4.5 Air vs GPT-4.1 Mini
- GLM 4.5 Air vs Qwen3 235B A22B Instruct 2507
- GLM 4.5 Air vs GLM 4.7 Flash
- GLM 4.5 Air vs Mercury 2
- GLM 4.5 Air vs GLM 4.5
- GLM 4.5 Air vs Qwen3 Coder 480B A35B
- GLM 4.5 Air vs Qwen3 Coder Next
- GLM 4.5 Air vs Mistral Small 4
- GLM 4.5 Air vs Qwen3 Next 80B A3B Instruct
- GLM 4.5 Air vs GLM 4.6V
- GLM 4.5 Air vs Trinity Large Thinking
- GLM 4.5 Air vs Llama 4 Maverick
- GLM 4.5 Air vs GLM 4.5V
Our take
GLM 4.5 Air is 1.3x cheaper for a typical chat. Qwen3 Next 80B A3B Thinking scores higher on the Artificial Analysis Intelligence Index (11.2 vs 11.1). Qwen3 Next 80B A3B Thinking has the larger context window (262K vs 131K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Qwen3 Next 80B A3B Thinking or GLM 4.5 Air cheaper?
GLM 4.5 Air is cheaper for a typical chat (2K input tokens and 500 output tokens). GLM 4.5 Air costs $0.13 per 1M input tokens and $0.85 per 1M output tokens, while Qwen3 Next 80B A3B Thinking costs $0.15 per 1M input tokens and $1.20 per 1M output tokens.
Which has a bigger context window, Qwen3 Next 80B A3B Thinking or GLM 4.5 Air?
Qwen3 Next 80B A3B Thinking supports up to 262K tokens of context, compared with 131K for GLM 4.5 Air.
Is Qwen3 Next 80B A3B Thinking smarter than GLM 4.5 Air?
On the Artificial Analysis Intelligence Index, Qwen3 Next 80B A3B Thinking scores 11.2 and GLM 4.5 Air scores 11.1, putting Qwen3 Next 80B A3B Thinking ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Qwen3 Next 80B A3B Thinking and GLM 4.5 Air at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3 Next 80B A3B Thinking and GLM 4.5 Air answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Qwen3 Next 80B A3B Thinking and GLM 4.5 Air at the same time. Compare the answers side by side and keep the best one.