Open coding-focused Qwen model for code generation, repair, and repository reasoning
Specification
most-agreed values
Context
33K
Max output
8K
Released
2024-11-12
Knowledge cutoff
—
Retires
2025-11-13
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.66
Output
$1.00
Cache read
$0.1003
Rate limits
Requests per minute
300
Available from 10 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| huggingface | $0.06 | $0.20 | — | — | 131K | 8K | — |
| nscale | $0.06 | $0.20 | — | — | — | — | — |
| hyperbolic | $0.12 | $0.30 | — | — | 33K | 33K | — |
| nano-gpt | $0.2006 | $0.2006 | $0.1003 | — | 32K | 8K | — |
| cloudflare | $0.66 | $1.00 | — | — | 33K | 33K | — |
| cloudflare-workers-ai · cf | $0.66 | $1.00 | — | — | 33K | 33K | — |
| edenai | $0.66 | $1.00 | — | — | 33K | 8K | — |
| together_ai | $0.80 | $0.80 | — | — | 16K | 16K | 2025-11-13 |
| ovhcloud · ovhcloud | $0.87 | $0.87 | — | — | 32K | 32K | — |
| fireworks_ai | $0.90 | $0.90 | — | — | 4K | 4K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-15 | together_ai | Input | $0.80 |
| 2026-09-24 | together_ai | Input | $0.80 |
| 2026-09-15 | together_ai | Output | $0.80 |
| 2026-09-24 | together_ai | Output | $0.80 |
More from Alibaba
most-hosted first