Qwen API pricing
Qwen API pricing: current per-token rates
Qwen's current API rates per 1M tokens, input / output / cached-read, verified 2026-10-20. Every rate links to its official source.
Current Qwen model prices
| Model | Input ($/1M) | Output ($/1M) | Cached in ($/1M) | Context |
|---|---|---|---|---|
| Qwen3.6 35B A3B | $0.10 | $0.95 | $0.05 | 262K |
| Qwen3.6 Plus | $0.33 | $1.95 | — | 1M |
| Qwen3.7 Flash | $0.03 | $0.13 | $0.01 | 1M |
| Qwen3.7 Max | $1.48 | $4.42 | $0.29 | 1M |
| Qwen3.7 Plus | $0.32 | $1.28 | $0.06 | 1M |
| Qwen3.8 27B | $0.24 | $2.20 | $0.05 | 1M |
| Qwen3.8 Flash | $0.15 | $0.47 | $0.02 | 1M |
| Qwen3.8 Max | $2 | $6 | $0.25 | 1M |
Non-official data by OpenRouter top-provider pricing (open-weight model, hosted by multiple providers — the top provider’s rate, not necessarily the creator’s first-party price); verify against the provider's own page before relying on it.
Recent price changes
- Qwen3.6 35B A3B: $0.15/$1 → $0.10/$0.95 per 1M (effective 2026-10-20)
- Qwen3.8 27B: $0.42/$2.55 → $0.24/$2.20 per 1M (effective 2026-10-15)
Common questions
Can I use the Qwen API for free?
No — API access is metered per token at the rates above. Subscriptions (where offered) bundle usage into a flat monthly price; the API itself is pay-as-you-go.
Which model is cheapest?
The lowest input/output rate in the table above for light work; match the model to the task rather than defaulting to the cheapest — routing the hard steps up and the cheap steps down usually beats a single choice.
Prices change. Verified 2026-10-20 — re-check the source before relying on them. Corrections: hello@aiarch.dev.
Learn to cost-model agents like an architect.
Free with an account: Track 0 (The Mindset Shift) and the Track 0 coach allowance, no card · every claim cited · full curriculum with membership
What a Claude agent actually costs, or compare Professional Membership pricing.