Alibaba Qwen · October 2026
Qwen API pricing, every model
41 Qwen models, from $0.03 to $4 per million input tokens. Qwen open and hosted models, from tiny to frontier-sized.
Prices from OpenRouter’s models API, updated October 29, 2026
Qwen3.7 Flash
$0.03 in · $0.13 outAbout $2.91 a month for a 1,000-chats-a-day support bot.
Qwen3.8 Max Prime
$4 in · $12 outReleased 2026-09-23, 1M tokens of context.
Qwen3.8 27B
−90%Cached input costs $0.0039 instead of $0.039 per 1M tokens.
All Qwen models and prices
| Model | Released | Input /1M | Output /1M | Cache read /1M | Batch in / out | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|---|
| Qwen3.8 Max Prime | 2026-09-23 | $4 | $12 | $0.50 | – | 1M | $324 |
| Qwen3.8 Omni Flash | 2026-09-21 | $0.15 | $0.47 | $0.016 | – | 1M | $12.39 |
| Qwen3.8 Max (0902) | 2026-09-03 | $2 | $6 | $0.25 | – | 1M | $162 |
| Qwen3.8 Flash | 2026-08-26 | $0.15 | $0.47 | $0.016 | – | 1M | $12.39 |
| Qwen3.8 27B | 2026-08-14 | $0.039 | $1.25 | $0.0039 | – | 1M | $16.75 |
| Qwen3.8 2.4T A95B | 2026-08-12 | $2 | $6 | $0.25 | – | 1.05M | $162 |
| Qwen3.7 Flash | 2026-07-27 | $0.03 | $0.13 | $0.006 | – | 1M | $2.91 |
| Qwen3.7 Plus | 2026-06-03 | $0.32 | $1.28 | $0.064 | $0.23 / $0.92 | 1M | $29.76 |
| Qwen3.7 Max | 2026-05-21 | $1.48 | $4.42 | $0.295 | – | 1M | $119 |
| Qwen3.5 Plus 2026-04-20 | 2026-04-27 | $0.30 | $1.80 | – | – | 1M | $35.10 |
| Qwen3.6 27B | 2026-04-27 | $0.45 | $2.70 | – | – | 262K | $52.65 |
| Qwen3.6 35B A3B | 2026-04-27 | $0.10 | $0.90 | $0.025 | – | 262K | $15.30 |
| Qwen3.6 Flash | 2026-04-27 | $0.188 | $1.13 | – | – | 1M | $21.94 |
| Qwen3.6 Plus | 2026-04-02 | $0.325 | $1.95 | – | – | 1M | $38.03 |
| Qwen3.5-9B | 2026-03-10 | $0.17 | $0.25 | – | – | 262K | $10.65 |
| Qwen3.5-122B-A10B | 2026-02-25 | $0.26 | $2.08 | – | – | 262K | $36.66 |
| Qwen3.5-27B | 2026-02-25 | $0.26 | $2.60 | – | – | 262K | $42.90 |
| Qwen3.5-35B-A3B | 2026-02-25 | $0.14 | $1 | $0.05 | – | 262K | $18.30 |
| Qwen3.5-Flash | 2026-02-25 | $0.065 | $0.26 | – | – | 1M | $6.04 |
| Qwen3.5 397B A17B | 2026-02-16 | $0.50 | $3.60 | $0.30 | – | 262K | $65.70 |
| Qwen3.5 Plus 2026-02-15 | 2026-02-16 | $0.26 | $1.56 | – | – | 1M | $30.42 |
| Qwen3 Coder Next | 2026-02-04 | $0.12 | $0.80 | $0.07 | – | 262K | $15.00 |
| Qwen3 VL 8B Instruct | 2025-10-14 | $0.25 | $0.75 | $0.12 | – | 262K | $20.25 |
| Qwen3 VL 30B A3B Instruct | 2025-10-06 | $0.15 | $0.60 | – | – | 262K | $13.95 |
| Qwen3 VL 30B A3B Thinking | 2025-10-06 | $0.29 | $1 | – | – | 262K | $25.05 |
| Qwen3 VL 235B A22B Instruct | 2025-09-23 | $0.21 | $1.90 | $0.10 | – | 262K | $32.25 |
| Qwen3 Coder Flash | 2025-09-17 | $0.195 | $0.975 | $0.039 | – | 1M | $20.48 |
| Qwen3 Next 80B A3B Instruct | 2025-09-11 | $0.09 | $1.10 | – | – | 262K | $17.25 |
| Qwen3 Coder 30B A3B Instruct | 2025-07-31 | $0.07 | $0.28 | – | – | 262K | $6.51 |
| Qwen3 30B A3B Instruct 2507 | 2025-07-29 | $0.10 | $0.30 | $0.10 | – | 262K | $8.10 |
| Qwen3 235B A22B Thinking 2507 | 2025-07-25 | $0.45 | $3.50 | – | – | 128K | $62.25 |
| Qwen3 Coder 480B A35B | 2025-07-23 | $0.30 | $1 | $0.10 | – | 262K | $25.50 |
| Qwen3 235B A22B Instruct 2507 | 2025-07-21 | $0.09 | $0.55 | – | – | 262K | $10.65 |
| Qwen3 14B | 2025-04-28 | $0.12 | $0.24 | – | – | 41K | $8.28 |
| Qwen3 30B A3B | 2025-04-28 | $0.12 | $0.50 | – | – | 41K | $11.40 |
| Qwen3 32B | 2025-04-28 | $0.08 | $0.28 | – | – | 131K | $6.96 |
| Qwen-Plus | 2025-02-01 | $0.26 | $0.78 | $0.052 | – | 1M | $21.06 |
| Qwen2.5 VL 72B Instruct | 2025-02-01 | $0.80 | $1 | $0.40 | – | 128K | $48.00 |
| Qwen2.5 Coder 32B Instruct | 2024-11-11 | $0.66 | $1 | – | – | 33K | $41.70 |
| Qwen2.5 7B Instruct | 2024-10-16 | $0.10 | $0.20 | – | – | 33K | $6.90 |
| Qwen2.5 72B Instruct | 2024-09-19 | $0.36 | $0.40 | – | – | 33K | $21.00 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
What three real workloads cost a month
| Model | Support chatbot | Daily summaries | Coding agent |
|---|---|---|---|
| Qwen3.7 Flash | $2.91 | $38.70 | $10.90 |
| Qwen3.5-Flash | $6.04 | $81.90 | $53.04 |
| Qwen3 Coder 30B A3B Instruct | $6.51 | $88.20 | $57.12 |
| Qwen2.5 7B Instruct | $6.90 | $108 | $76.80 |
| Qwen3 32B | $6.96 | $97.20 | $64.32 |
| Qwen3 14B | $8.28 | $130 | $92.16 |
| Qwen3 30B A3B Instruct 2507 | $8.10 | $117 | $79.20 |
| Qwen3.5-9B | $10.65 | $176 | $128 |
Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out · Daily summaries: 10,000 a day, 3,000 tokens in, 300 out · Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out. Cached share billed at the cache-read price where the model has one.
Compare with other providers
Qwen pricing questions
How much does the Qwen API cost?
Alibaba Qwen’s models range from $0.03 per 1M input tokens and $0.13 per 1M output tokens (Qwen3.7 Flash) to $4 and $12 (Qwen3.8 Max Prime). The newest, Qwen3.8 Max Prime, costs $4 in and $12 out.
Which Qwen model is the cheapest?
Qwen3.7 Flash, at $0.03 per 1M input tokens. A support chatbot doing 1,000 chats a day would cost about $2.91 a month on it.
Does Alibaba Qwen discount cached prompts?
Yes. On Qwen3.8 27B, cached input costs $0.0039 per 1M tokens instead of $0.039, 90% less. Long, repeated system prompts and agent loops benefit most.
Is there a batch discount?
1 Qwen models have a batch price, typically half the normal rate, for jobs that can wait (up to 24 hours). See the Batch column below.
How do I track my Qwen spend per product?
Route it through OpenRouter with one API key per product and connect OpenRouter to Glow: you get spend by model, API key and product every day, with cache hit rate. Track AI spend.
See your real Qwen bill.
Glow shows what you actually spend by model, API key and product, every day, and which cheaper model would do the same job.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial