Back to models
available
Qwen: Qwen3.8 Flash
qwen/qwen3-8-flashPrices
- Input
$0.18 per 1M tokens
low- Input (cache write)
$0.20 per 1M tokens
low- Input (cached read)
$0.016 per 1M tokens
low- Output
$0.564 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 | $0.16 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Alibaba Model Studio | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Alibaba Model Studio · alibaba-cn | Input | $0.1188 per 1M tokens |
| Input (cache write) | $0.1855 per 1M tokens | |
| Input (cached read) | $0.0148 per 1M tokens | |
| Output | $0.4007 per 1M tokens | |
| Alibaba Model Studio · ofox | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Alibaba Model Studio · vercel | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| OpenRouter | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| OpenRouter · qwen | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Token plan · alibaba-token-plan | Input | $0.00 per 1M tokens |
| Input (cache write) | $0.00 per 1M tokens | |
| Input (cached read) | $0.00 per 1M tokens | |
| Output | $0.00 per 1M tokens | |
| Token plan · alibaba-token-plan-cn | Input | $0.00 per 1M tokens |
| Input (cache write) | $0.00 per 1M tokens | |
| Input (cached read) | $0.00 per 1M tokens | |
| Output | $0.00 per 1M tokens | |
| Other · 302ai | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · aihubmix | Input | $0.1126 per 1M tokens |
| Input (cache write) | $0.1759 per 1M tokens | |
| Input (cached read) | $0.0141 per 1M tokens | |
| Output | $0.38 per 1M tokens | |
| Other · boundless | Input | $0.15 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · commandcode | Input | $0.16 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · crossmodel | Input | $0.13 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.43 per 1M tokens | |
| Other · deepinfra | Input | $0.113 per 1M tokens |
| Input (cached read) | $0.0141 per 1M tokens | |
| Output | $0.382 per 1M tokens | |
| Other · edenai | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · empiriolabs | Input | $0.16 per 1M tokens |
| Input (cached read) | $0.16 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Web search (context size: high) | $0.02 per query | |
| Web search (context size: low) | $0.02 per query | |
| Web search (context size: medium) | $0.02 per query | |
| Other · gmi | Input | $0.16 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · gmicloud | Input | $0.16 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · hyper | Input | $0.15 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · inferenceapis | Input | $0.15 per 1M tokens |
| Input (cached read) | $0.02 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Other · iteracompute | Input | $0.11 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.38 per 1M tokens | |
| Other · kilo | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · kyma | Input | $0.2045 per 1M tokens |
| Output | $0.641 per 1M tokens | |
| Other · llmgateway | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · llmgateway-providers | Input (cached read) (host: canopywave) | $0.02 per 1M tokens |
| Input (cached read) (host: novita) | $0.016 per 1M tokens | |
| Input (host: canopywave) | $0.15 per 1M tokens | |
| Input (host: novita) | $0.15 per 1M tokens | |
| Output (host: canopywave) | $0.50 per 1M tokens | |
| Output (host: novita) | $0.47 per 1M tokens | |
| Other · merge-gateway | Input | $0.15 per 1M tokens |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · nano-gpt | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · novita-ai | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · ofox | Input | $0.11 per 1M tokens |
| Input (cache write) | $0.14 per 1M tokens | |
| Input (cached read) | $0.011 per 1M tokens | |
| Output | $0.39 per 1M tokens | |
| Other · opencode | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · opencode-go | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · openrouter | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · requesty | Input | $0.16 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · runcrate | Input | $0.1187 per 1M tokens |
| Input (cached read) | $0.0148 per 1M tokens | |
| Output | $0.4011 per 1M tokens | |
| Other · scnet | Input | $0.00 per 1M tokens |
| Input (cached read) | $0.00 per 1M tokens | |
| Output | $0.00 per 1M tokens | |
| Other · standardcompute | Input | $0.15 per 1M tokens |
| Input (cache write) | $0.20 per 1M tokens | |
| Input (cached read) | $0.016 per 1M tokens | |
| Output | $0.47 per 1M tokens | |
| Other · together-ai | Input | $0.15 per 1M tokens |
| Output | $0.47 per 1M tokens | |
| Other · vancine | Input | $0.12 per 1M tokens |
| Input (cached read) | $0.013 per 1M tokens | |
| Output | $0.38 per 1M tokens | |
| Other · zenifra | Input | $0.1088 per 1M tokens |
| Input (cached read) | $0.0181 per 1M tokens | |
| Output | $0.3627 per 1M tokens |
Specifications
- Provider
- qwen
- Context window
- 1,000,000
- Max output tokens
- 131,072
- Open weights
- no
- Released
- 08/26/2026
- Retires
- no date announced
- First seen by this tracker
Price history
Input — per 1M tokens
| From | Amount |
|---|---|
| 09/17/2026 | 0.15 |
| 09/20/2026 | 0.1126 |
| 09/23/2026 | 0.18 |
Output — per 1M tokens
| From | Amount |
|---|---|
| 09/17/2026 | 0.47 |
| 09/20/2026 | 0.38 |
| 09/23/2026 | 0.564 |
Input (cached read) — per 1M tokens
| From | Amount |
|---|---|
| 09/17/2026 | 0.016 |
| 09/20/2026 | 0.0141 |
| 09/23/2026 | 0.013 |
| 10/19/2026 | 0.016 |
Input (cache write) — per 1M tokens
| From | Amount |
|---|---|
| 09/17/2026 | 0.2 |
| 09/20/2026 | 0.1759 |
| 10/19/2026 | 0.2 |