Qwen API pricing
Every Qwen model we track, per 1M tokens, from the official pricing page.
Quick answer: Qwen API prices run from $0.15 in and $0.47 out per 1M tokens (Qwen3.8 Flash) up to $2 in and $6 out (Qwen3.8 Max). Its cheapest model is number 2 of 29 on our full list. Checked Oct 16, 2026 against the official pricing page.
| Model | Input | Cached | Output | Context |
|---|---|---|---|---|
| Qwen3.8 Flashqwen3.8-flashInternational (Singapore). Cache hits billed at 10% of input. | $0.15 | $0.015 | $0.47 | 1M |
| Qwen3.7 Plusqwen3.7-plusList price, prompts up to 256K. Limited-time 20% off. | $0.40 | $0.04 | $1.60 | 1M |
| Qwen3.8 Maxqwen3.8-maxInternational (Singapore). Cache hits billed at 10% of input. | $2 | $0.20 | $6 | 1M |
Qwen3.8 Flashqwen3.8-flash
1M context$0.15Input
$0.47Output
$0.015Cached
Qwen3.7 Plusqwen3.7-plus
1M context$0.40Input
$1.60Output
$0.04Cached
Qwen3.8 Maxqwen3.8-max
1M context$2Input
$6Output
$0.20Cached
How it compares
Cheapest models from other providers, blended per 1M tokens: GPT-6 Luna (OpenAI) $0.20 · Mistral Small 4 (Mistral) $0.26 · DeepSeek V4.1 Flash (DeepSeek) $0.53. See the full API price table, the best model for each task or the plan vs API calculator.
FAQ
How much does the Qwen API cost?
From $0.15 input and $0.47 output per 1M tokens for Qwen3.8 Flash, up to $2 and $6 for Qwen3.8 Max.
What is the cheapest Qwen model?
Qwen3.8 Flash, with a blended price of $0.23 per 1M tokens (3 parts input to 1 part output).
Is a subscription cheaper than the Qwen API?
It depends on how much you use it. Try our plan vs API calculator with your own usage.
Other providers: OpenAI · Anthropic · Google · Meta · DeepSeek · Mistral · xAI