Qwen3.5 Plus 2026-04-20 vs Qwen3.7 Plus
Qwen3.5 Plus 2026-04-20 (Qwen) and Qwen3.7 Plus (Qwen) are listed at different prices. Qwen3.5 Plus 2026-04-20 costs less for input, $0.30 per 1M tokens against $0.32; Qwen3.7 Plus costs less for output, $1.28 per 1M tokens against $1.80. Both hold 1,000,000 tokens of context. Qwen3.7 Plus can write up to 131,072 tokens in one response, against 65,536 for Qwen3.5 Plus 2026-04-20. Qwen3.5 Plus 2026-04-20 accepts text, images and video and produces text; Qwen3.7 Plus accepts text and images and produces text.
Qwen: Qwen3.5 Plus 2026-04-20 accepts text, image, and video, while Qwen: Qwen3.7 Plus accepts text and image; both produce text, support tools, structured outputs, response formats, and reasoning, and have a 1-million-token context window. Their maximum output limits are 65,536 and 131,072 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Qwen3.5 Plus 2026-04-20 | Qwen3.7 Plus |
|---|---|---|
| Maker | Qwen | Qwen |
| Added to catalog | 27 Apr 2026 | 3 Jun 2026 |
| Input, per 1M tokens | $0.30 | $0.32 |
| Output, per 1M tokens | $1.80 | $1.28 |
| Input above 256K tokensPer 1M; long prompts | $0.375 | $0.96 |
| Output above 256K tokens | $2.25 | $3.84 |
| Cached input read, per 1M | n/a | $0.064 |
| Context windowTokens | 1,000,000 | 1,000,000 |
| Max outputTokens | 65,536 | 131,072 |
| Accepts | image, text, video | image, text |
| Produces | text | text |
| Tool calling | Yes | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | No |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Qwen3.5 Plus 2026-04-20 | Qwen3.7 Plus |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0007 | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0089 | $0.0090 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.013 | $0.012 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.048 | $0.050 |
Which to choose
Choose Qwen3.5 Plus 2026-04-20 if
- Input tokens cost less: $0.30 against $0.32 per 1M
- Your prompts often run past 256K tokens: $0.375 against $0.96 per 1M input tokens there
- It has to read video, which the other model does not
Choose Qwen3.7 Plus if
- Output tokens cost less: $1.28 against $1.80 per 1M
- Cached input costs less: $0.064 against n/a per 1M
- You need longer answers in one response: 131,072 tokens against 65,536
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.