Qwen3 Coder 480B A35B vs Qwen3.5 Plus 2026-04-20
Qwen3 Coder 480B A35B (Qwen) and Qwen3.5 Plus 2026-04-20 (Qwen) are listed at different prices. Qwen3 Coder 480B A35B costs less: $0.30 per 1M input tokens and $1.00 per 1M output tokens, against $0.30 and $1.80 for Qwen3.5 Plus 2026-04-20. Qwen3.5 Plus 2026-04-20 has the larger context window, 1,000,000 tokens against 262,144 for Qwen3 Coder 480B A35B. Qwen3.5 Plus 2026-04-20 charges $0.375 and $2.25 per 1M once a prompt passes 256,000 tokens; Qwen3 Coder 480B A35B keeps one price across its window. Qwen3 Coder 480B A35B accepts text and produces text; Qwen3.5 Plus 2026-04-20 accepts text, images and video and produces text.
Qwen: Qwen3 Coder 480B A35B accepts text, while Qwen: Qwen3.5 Plus 2026-04-20 accepts text, image, and video; both produce text and support tools, structured outputs, and response formats. Their context windows are 262,144 and 1,000,000 tokens, respectively, and both allow up to 65,536 output tokens.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Qwen3 Coder 480B A35B | Qwen3.5 Plus 2026-04-20 |
|---|---|---|
| Maker | Qwen | Qwen |
| Added to catalog | 23 Jul 2025 | 27 Apr 2026 |
| Input, per 1M tokens | $0.30 | $0.30 |
| Output, per 1M tokens | $1.00 | $1.80 |
| Input above 256K tokensPer 1M; long prompts | $0.30 | $0.375 |
| Output above 256K tokens | $1.00 | $2.25 |
| Cached input read, per 1M | $0.10 | n/a |
| Context windowTokens | 262,144 | 1,000,000 |
| Max outputTokens | 65,536 | 65,536 |
| Accepts | text | image, text, video |
| 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 Coder 480B A35B | Qwen3.5 Plus 2026-04-20 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0005 | $0.0007 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0083 | $0.0089 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.011 | $0.013 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.047 | $0.048 |
Which to choose
Choose Qwen3 Coder 480B A35B if
- Output tokens cost less: $1.00 against $1.80 per 1M
- Your prompts often run past 256K tokens: $0.30 against $0.375 per 1M input tokens there
- Cached input costs less: $0.10 against n/a per 1M
Choose Qwen3.5 Plus 2026-04-20 if
- You need the larger context window: 1,000,000 tokens against 262,144
- It has to read images and video, which the other model does not
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.