Qwen3 Max Thinking pricing
$$ Standard$0.78/M input · $3.90/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
Full rate table
| Rate | Price | Unit |
|---|---|---|
| Input | 0.78 | /M tokens |
| Output | 3.9 | /M tokens |
What typical work costs
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0027 |
| Long-document summary | 60K tokens in, 2K out | $0.05 |
| Agent working session | 400K tokens in, 40K out across a day | $0.47 |
Price your own workload
- Per call
- $0.0027
- Per month
- $0.27
Compare up to four models at once in the cost calculator.
Frequently asked
What does Qwen3 Max Thinking cost per 1M tokens?
Qwen3 Max Thinking lists at $0.78 per 1M input tokens and $3.90 per 1M output tokens.
What does a typical chat message with Qwen3 Max Thinking cost?
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0027 at list price. Long documents and long replies scale that linearly with token counts.
Is Qwen3 Max Thinking cheaper than Qwen3 14B?
Qwen3 14B has the lower blended price at a 3:1 input:output mix. Qwen3 Max Thinking: $0.78 in / $3.90 out per 1M. Qwen3 14B: $0.10 in / $0.24 out per 1M.
How does idapt bill Qwen3 Max Thinking?
Chat with Qwen3 Max Thinking in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the Qwen3 Max Thinking model page · cheapest models board · price changes