AI model comparison
Qwen3 Coder 30B A3B Instruct vs Qwen2.5 72B Instruct
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use.
- Input / 1M
- $0.07
- Output / 1M
- $0.28
- Context
- 262K
Qwen2.5 72B is the latest series of Qwen large language models.
- Input / 1M
- $0.36
- Output / 1M
- $0.40
- Context
- 33K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Qwen3 Coder 30B A3B Instruct
3.3x cheaper for a typical chat
Higher intelligence score
Qwen3 Coder 30B A3B Instruct
9.6 vs 7.7 on Artificial Analysis
Larger context window
Qwen3 Coder 30B A3B Instruct
262K vs 33K tokens
Newer release
Qwen3 Coder 30B A3B Instruct
Released July 31, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Qwen3 Coder 30B A3B Instruct9.6Qwen2.5 72B Instruct7.7Coding index
Qwen3 Coder 30B A3B InstructNot availableQwen2.5 72B InstructNot availableAgentic index
Qwen3 Coder 30B A3B InstructNot availableQwen2.5 72B InstructNot availablePricing
Qwen3 Coder 30B A3B Instruct vs Qwen2.5 72B Instruct API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Qwen3 Coder 30B A3B Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Input tokensPer 1M tokens | $0.07 | $0.36 |
| Output tokensPer 1M tokens | $0.28 | $0.40 |
| Cached input (read)Per 1M tokens | Not available | Not available |
| 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 Coder 30B A3B Instruct$0.28Qwen2.5 72B Instruct$0.92Coding task
30K in, 4K out
Qwen3 Coder 30B A3B Instruct$3.22Qwen2.5 72B Instruct$12.40Long document summary
150K in, 2K out
Qwen3 Coder 30B A3B Instruct$11.06Qwen2.5 72B Instruct$54.80Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Qwen3 Coder 30B A3B Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Context window | 262K tokens | 33K tokens |
| Max output | 236K tokens | 16K 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 | July 31, 2025 | September 19, 2024 |
Features
Supported features
API features available for each model.
| Metric | Qwen3 Coder 30B A3B Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Not 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 Coder 30B A3B InstructView full model details- Qwen3 Coder 30B A3B Instruct vs Gemini 2.5 Flash Lite
- Qwen3 Coder 30B A3B Instruct vs gpt-oss-120b
- Qwen3 Coder 30B A3B Instruct vs Qwen3 235B A22B Instruct 2507
- Qwen3 Coder 30B A3B Instruct vs Qwen3.5-9B
- Qwen3 Coder 30B A3B Instruct vs Qwen3 30B A3B Instruct 2507
- Qwen3 Coder 30B A3B Instruct vs Granite 4.2 8B
- Qwen3 Coder 30B A3B Instruct vs Qwen3 Coder Next
- Qwen3 Coder 30B A3B Instruct vs Qwen3 Next 80B A3B Instruct
- Qwen3 Coder 30B A3B Instruct vs Nemotron 3 Nano 30B A3B
- Qwen3 Coder 30B A3B Instruct vs Qwen3 32B
- Qwen3 Coder 30B A3B Instruct vs Qwen3 14B
- Qwen3 Coder 30B A3B Instruct vs Qwen3 VL 30B A3B Instruct
Qwen2.5 72B InstructView full model details- Qwen2.5 72B Instruct vs Gemini 2.5 Flash Lite
- Qwen2.5 72B Instruct vs Gemma 3 27B
- Qwen2.5 72B Instruct vs Qwen3 30B A3B Instruct 2507
- Qwen2.5 72B Instruct vs Llama 3.3 70B Instruct
- Qwen2.5 72B Instruct vs Qwen3 32B
- Qwen2.5 72B Instruct vs Qwen3 14B
- Qwen2.5 72B Instruct vs GPT-4.1 Nano
- Qwen2.5 72B Instruct vs Llama 4 Scout
- Qwen2.5 72B Instruct vs Qwen3 VL 30B A3B Instruct
- Qwen2.5 72B Instruct vs Solar Pro 3
- Qwen2.5 72B Instruct vs Qwen3 30B A3B
- Qwen2.5 72B Instruct vs Qwen3 VL 8B Instruct
- Qwen2.5 72B Instruct vs Qwen2.5 Coder 32B Instruct
- Qwen2.5 72B Instruct vs Llama 3.1 70B Instruct
Our take
Qwen3 Coder 30B A3B Instruct is 3.3x cheaper for a typical chat. Qwen3 Coder 30B A3B Instruct scores higher on the Artificial Analysis Intelligence Index (9.6 vs 7.7). Qwen3 Coder 30B A3B Instruct has the larger context window (262K vs 33K 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 Coder 30B A3B Instruct or Qwen2.5 72B Instruct cheaper?
Qwen3 Coder 30B A3B Instruct is cheaper for a typical chat (2K input tokens and 500 output tokens). Qwen3 Coder 30B A3B Instruct costs $0.07 per 1M input tokens and $0.28 per 1M output tokens, while Qwen2.5 72B Instruct costs $0.36 per 1M input tokens and $0.40 per 1M output tokens.
Which has a bigger context window, Qwen3 Coder 30B A3B Instruct or Qwen2.5 72B Instruct?
Qwen3 Coder 30B A3B Instruct supports up to 262K tokens of context, compared with 33K for Qwen2.5 72B Instruct.
Is Qwen3 Coder 30B A3B Instruct smarter than Qwen2.5 72B Instruct?
On the Artificial Analysis Intelligence Index, Qwen3 Coder 30B A3B Instruct scores 9.6 and Qwen2.5 72B Instruct scores 7.7, putting Qwen3 Coder 30B A3B Instruct ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Qwen3 Coder 30B A3B Instruct and Qwen2.5 72B Instruct at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3 Coder 30B A3B Instruct and Qwen2.5 72B Instruct answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Qwen3 Coder 30B A3B Instruct and Qwen2.5 72B Instruct at the same time. Compare the answers side by side and keep the best one.