AI model comparison
Qwen3 235B A22B Thinking 2507 vs R1 0528
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks.
- Input / 1M
- $0.45
- Output / 1M
- $3.50
- Context
- 128K
DeepSeek
R1 0528
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens.
- Input / 1M
- $0.50
- Output / 1M
- $2.15
- Context
- 164K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
R1 0528
1.3x cheaper for a typical chat
Higher intelligence score
R1 0528
13.1 vs 12.7 on Artificial Analysis
Larger context window
R1 0528
164K vs 128K tokens
Newer release
Qwen3 235B A22B Thinking 2507
Released July 25, 2025
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Qwen3 235B A22B Thinking 250712.7R1 052813.1Coding index
Qwen3 235B A22B Thinking 250722.1R1 0528Not availableAgentic index
Qwen3 235B A22B Thinking 25071.3R1 0528Not availablePricing
Qwen3 235B A22B Thinking 2507 vs R1 0528 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Qwen3 235B A22B Thinking 2507 | R1 0528 |
|---|---|---|
| Input tokensPer 1M tokens | $0.45 | $0.50 |
| Output tokensPer 1M tokens | $3.50 | $2.15 |
| Cached input (read)Per 1M tokens | Not available | $0.35 |
| 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 235B A22B Thinking 2507$2.65R1 0528$2.08Coding task
30K in, 4K out
Qwen3 235B A22B Thinking 2507$27.50R1 0528$23.60$19.10 cachedLong document summary
150K in, 2K out
Qwen3 235B A22B Thinking 2507$74.50R1 0528$79.30$56.80 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Qwen3 235B A22B Thinking 2507 | R1 0528 |
|---|---|---|
| Context window | 128K tokens | 164K tokens |
| Max output | 16K tokens | 33K 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 25, 2025 | May 28, 2025 |
Features
Supported features
API features available for each model.
| Metric | Qwen3 235B A22B Thinking 2507 | R1 0528 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Not supported | Supported |
| JSON mode | Not supported | Supported |
| Reasoning | Supported | 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 235B A22B Thinking 2507View full model details- Qwen3 235B A22B Thinking 2507 vs Gemini 2.5 Flash
- Qwen3 235B A22B Thinking 2507 vs Mistral Medium 3.5
- Qwen3 235B A22B Thinking 2507 vs Nova 2 Lite
- Qwen3 235B A22B Thinking 2507 vs Command A
- Qwen3 235B A22B Thinking 2507 vs GLM 4.5
- Qwen3 235B A22B Thinking 2507 vs GPT-4.1
- Qwen3 235B A22B Thinking 2507 vs Kimi K2 0711
- Qwen3 235B A22B Thinking 2507 vs o3 Mini
- Qwen3 235B A22B Thinking 2507 vs Qwen3 235B A22B Instruct 2507
- Qwen3 235B A22B Thinking 2507 vs Qwen3 Coder 480B A35B
- Qwen3 235B A22B Thinking 2507 vs Sonar Reasoning Pro
- Qwen3 235B A22B Thinking 2507 vs o3 Mini High
- Qwen3 235B A22B Thinking 2507 vs Qwen3 VL 235B A22B Instruct
R1 0528View full model details- R1 0528 vs Gemini 3.1 Flash Lite
- R1 0528 vs Gemini 2.5 Flash
- R1 0528 vs Kimi K2 0905
- R1 0528 vs DeepSeek V3.1 Terminus
- R1 0528 vs DeepSeek V3.1
- R1 0528 vs Nova 2 Lite
- R1 0528 vs Command A
- R1 0528 vs GLM 4.5
- R1 0528 vs Kimi K2 0711
- R1 0528 vs o3 Mini
- R1 0528 vs MiniMax M1
- R1 0528 vs R1
- R1 0528 vs DeepSeek V3 0324
Our take
R1 0528 is 1.3x cheaper for a typical chat. R1 0528 scores higher on the Artificial Analysis Intelligence Index (13.1 vs 12.7). R1 0528 has the larger context window (164K vs 128K 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 235B A22B Thinking 2507 or R1 0528 cheaper?
R1 0528 is cheaper for a typical chat (2K input tokens and 500 output tokens). R1 0528 costs $0.50 per 1M input tokens and $2.15 per 1M output tokens, while Qwen3 235B A22B Thinking 2507 costs $0.45 per 1M input tokens and $3.50 per 1M output tokens.
Which has a bigger context window, Qwen3 235B A22B Thinking 2507 or R1 0528?
R1 0528 supports up to 164K tokens of context, compared with 128K for Qwen3 235B A22B Thinking 2507.
Is Qwen3 235B A22B Thinking 2507 smarter than R1 0528?
On the Artificial Analysis Intelligence Index, Qwen3 235B A22B Thinking 2507 scores 12.7 and R1 0528 scores 13.1, putting R1 0528 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Qwen3 235B A22B Thinking 2507 and R1 0528 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Qwen3 235B A22B Thinking 2507 and R1 0528 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Qwen3 235B A22B Thinking 2507 and R1 0528 at the same time. Compare the answers side by side and keep the best one.