Qwen models
llm11 can call 53 Qwen models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $0.055 to $6.00 per million tokens. The newest is Qwen3.8 Max Prime, released 2026-09-23.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen3.8 Max Prime | $4.00 | $12 | 1M | |
| Qwen3.8 Omni Flash | $0.150 | $0.470 | 1M | |
| Qwen3.8 Max (0902) | $2.00 | $6.00 | 1M | |
| Qwen3.8 Flash | $0.150 | $0.470 | 1M | |
| Qwen3.8 27B | $0.045 | $4.40 | 1M | |
| Qwen3.8 2.4T A95B | $2.00 | $6.00 | 1.05M | |
| Qwen3.7 Flash | $0.030 | $0.130 | 1M | |
| Qwen3.7 Plus | $0.320 | $1.28 | 1M | |
| Qwen3.7 Max | $1.48 | $4.42 | 1M | |
| Qwen3.5 Plus 2026-04-20 | $0.300 | $1.80 | 1M | |
| Qwen3.6 27B | $0.320 | $3.20 | 262K | |
| Qwen3.6 35B A3B | $0.150 | $1.00 | 262K | |
| Qwen3.6 Flash | $0.188 | $1.13 | 1M | |
| Qwen3.6 Max PreviewRetires 2026-10-09 | $1.03 | $6.16 | 262K | |
| Qwen3.6 Plus | $0.325 | $1.95 | 1M | |
| Qwen3.5-9B | $0.100 | $0.150 | 262K | |
| Qwen3.5-122B-A10B | $0.260 | $2.08 | 262K | |
| Qwen3.5-27B | $0.195 | $1.56 | 262K | |
| Qwen3.5-35B-A3B | $0.163 | $1.30 | 262K | |
| Qwen3.5-Flash | $0.065 | $0.260 | 1M | |
| Qwen3.5 397B A17B | $0.550 | $3.50 | 262K | |
| Qwen3.5 Plus 2026-02-15 | $0.260 | $1.56 | 1M | |
| Qwen3 Max ThinkingRetires 2026-10-09 | $0.780 | $3.90 | 262K | |
| Qwen3 Coder Next | $0.120 | $0.800 | 262K | |
| Qwen3 VL 32B InstructRetires 2026-10-09 | $0.104 | $0.416 | 131K | |
| Qwen3 VL 8B InstructRetires 2026-10-09 | $0.117 | $0.455 | 262K | |
| Qwen3 VL 8B ThinkingRetires 2026-10-09 | $0.180 | $2.10 | 131K | |
| Qwen3 VL 30B A3B Instruct | $0.150 | $0.600 | 262K | |
| Qwen3 VL 30B A3B ThinkingRetires 2026-10-09 | $0.200 | $2.40 | 262K | |
| Qwen3 Coder PlusRetires 2026-10-09 | $0.650 | $3.25 | 1M | |
| Qwen3 MaxRetires 2026-10-09 | $0.780 | $3.90 | 262K | |
| Qwen3 VL 235B A22B Instruct | $0.210 | $1.90 | 262K | |
| Qwen3 VL 235B A22B ThinkingRetires 2026-10-09 | $0.400 | $4.00 | 131K | |
| Qwen3 Coder Flash | $0.195 | $0.975 | 1M | |
| Qwen3 Next 80B A3B Instruct | $0.100 | $1.10 | 262K | |
| Qwen3 Next 80B A3B Thinking | $0.150 | $1.20 | 262K | |
| Qwen3 30B A3B Thinking 2507Retires 2026-10-09 | $0.200 | $2.40 | 82K | |
| Qwen3 Coder 30B A3B Instruct | $0.070 | $0.280 | 262K | |
| Qwen3 30B A3B Instruct 2507 | $0.048 | $0.193 | 262K | |
| Qwen3 235B A22B Thinking 2507Retires 2026-10-09 | $0.230 | $2.30 | 131K | |
| Qwen3 Coder 480B A35B | $0.300 | $1.00 | 262K | |
| Qwen3 235B A22B Instruct 2507 | $0.087 | $0.350 | 262K | |
| Qwen3 14B | $0.120 | $0.240 | 131K | |
| Qwen3 235B A22BRetires 2026-10-09 | $0.455 | $1.82 | 131K | |
| Qwen3 30B A3B | $0.120 | $0.500 | 131K | |
| Qwen3 32B | $0.080 | $0.280 | 131K | |
| Qwen3 8BRetires 2026-10-09 | $0.117 | $0.455 | 131K | |
| Qwen-Plus | $0.260 | $0.780 | 1M | |
| Qwen2.5 VL 72B Instruct | $0.800 | $1.00 | 128K | |
| Qwen2.5 Coder 32B Instruct | $0.660 | $1.00 | 33K | |
| Qwen2.5 7B Instruct | $0.100 | $0.200 | 33K | |
| Qwen2.5 72B Instruct | $0.360 | $0.400 | 33K |
Read from the live catalogue and refreshed daily. Prices are per million tokens.
Dated snapshots
Fixed versions of a model listed above, for when you need output that does not shift under you.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Plus 0728Retires 2026-10-09 | $0.260 | $0.780 | 1M |
Questions
- Which Qwen models can I call through llm11?
- 53 today, listed with live prices on this page. The list follows the upstream catalogue, so a new Qwen model appears here without anyone editing the page.
- What is the cheapest and the most expensive Qwen model?
- By blended price, weighting three parts input to one part output: Qwen3.7 Flash is cheapest at $0.055 per million tokens, and Qwen3.8 Max Prime is the most expensive at $6.00.
- What is the newest Qwen model?
- Qwen3.8 Max Prime, released 2026-09-23. Call it with model set to qwen/qwen3.8-max-prime.