Qwen3 30B A3B Instruct 2507 vs Qwen3.6 35B A3B
Qwen3 30B A3B Instruct 2507 (Qwen) and Qwen3.6 35B A3B (Qwen) are listed at different prices. Qwen3 30B A3B Instruct 2507 costs less: $0.10 per 1M input tokens and $0.30 per 1M output tokens, against $0.10 and $0.90 for Qwen3.6 35B A3B. Both hold 262,144 tokens of context. Qwen3 30B A3B Instruct 2507 accepts text and produces text; Qwen3.6 35B A3B accepts text, images and video and produces text.
Qwen: Qwen3 30B A3B Instruct 2507 accepts text and produces text, while Qwen: Qwen3.6 35B A3B also accepts images and video. Both have a 262,144-token context and support tools, structured outputs, and response formats; reasoning support is listed only for Qwen3.6.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Qwen3 30B A3B Instruct 2507 | Qwen3.6 35B A3B |
|---|---|---|
| Maker | Qwen | Qwen |
| Added to catalog | 29 Jul 2025 | 27 Apr 2026 |
| Input, per 1M tokens | $0.10 | $0.10 |
| Output, per 1M tokens | $0.30 | $0.90 |
| Cached input read, per 1M | $0.10 | $0.025 |
| Context windowTokens | 262,144 | 262,144 |
| Max outputTokens | 235,929 | 235,929 |
| 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 30B A3B Instruct 2507 | Qwen3.6 35B A3B |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0001 | $0.0003 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0027 | $0.0032 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0036 | $0.0048 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.015 | $0.016 |
Which to choose
Choose Qwen3 30B A3B Instruct 2507 if
- Output tokens cost less: $0.30 against $0.90 per 1M
Choose Qwen3.6 35B A3B if
- Cached input costs less: $0.025 against $0.10 per 1M
- 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.