Back to models
available
Qwen: Qwen3.8 Max Prime
qwen/qwen3-8-max-primePrices
- Input
$5.50 per 1M tokens
low- Input (cache write)
$5.00 per 1M tokens
low- Input (cached read)
$0.6877 per 1M tokens
low- Output
$16.50 per 1M tokens
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Alibaba Model Studio · aimlapi | Input | $4.23 per 1M tokens |
| Input (cached read) | $0.529 per 1M tokens | |
| Output | $12.70 per 1M tokens | |
| Alibaba Model Studio · vercel | Input | $4.00 per 1M tokens |
| Input (cache write) | $5.00 per 1M tokens | |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| OpenRouter | Input | $4.00 per 1M tokens |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| OpenRouter · qwen | Input | $4.00 per 1M tokens |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Other · commandcode | Input | $4.00 per 1M tokens |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Other · kilo | Input | $4.00 per 1M tokens |
| Input (cache write) | $5.00 per 1M tokens | |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Other · nano-gpt | Input | $4.00 per 1M tokens |
| Input (cached read) | $0.50 per 1M tokens | |
| Output | $12.00 per 1M tokens |
Specifications
- Provider
- qwen
- Context window
- 1,000,000
- Max output tokens
- 131,072
- Open weights
- no
- Released
- 09/23/2026
- Retires
- no date announced
- First seen by this tracker
Price history
Input — per 1M tokens
| From | Amount |
|---|---|
| 09/25/2026 | 4 |
| 10/14/2026 | 5.5 |
Output — per 1M tokens
| From | Amount |
|---|---|
| 09/25/2026 | 12 |
| 10/14/2026 | 16.5 |
Input (cached read) — per 1M tokens
| From | Amount |
|---|---|
| 09/25/2026 | 0.5 |
| 10/14/2026 | 0.6877 |
No changes recorded
- Input (cache write)
- 5 per 1M tokens, unchanged since 09/29/2026