Qwen3.6 Max API Pricing
Qwen3.6 Max costs $1.30 per 1M input tokens and $7.80 per 1M output tokens on Alibaba's API. Cached input is billed at $0.13 per 1M tokens. Prices are provider list prices in USD, refreshed as sources update; see the Qwen3.6 Max model profile for capability scores.
Price List
| Rate | Price (USD) | Notes |
|---|---|---|
| Input | $1.30 | per 1M tokens |
| Output | $7.80 | per 1M tokens |
| Cached input (read) | $0.13 | per 1M tokens |
| Cache write | $1.63 | per 1M tokens |
| Blended input + output | $9.10 | 1M in + 1M out at list price |
What a Workload Costs
Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of Qwen3.6 Max.
| Workload | Cost | Tokens |
|---|---|---|
| Short chat turn | $0.00520 | 1K in / 500 out |
| Summarize a long document | $0.146 | 100K in / 2K out |
| Agentic coding session | $1.43 | 500K in / 100K out |
| 1M input + 1M output tokens | $9.10 | 1M in / 1M out |
Effective Cost
In AI IQ's scoring, Qwen3.6 Max's list price is adjusted by a token-usage multiplier of 1.796 (measured from real benchmark runs), giving an effective cost of $16.34 per 1M input + output tokens. That places it #90 of 117 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.
Cheaper Alternatives at Similar Capability
Models with a lower effective cost that score within a few IQ points of Qwen3.6 Max (IQ 114), or better.
| Model | Provider | IQ | Effective Cost / 1M |
|---|---|---|---|
| gpt-5.6-luna | OpenAI | 129 | $9.29 |
| gemini-3.1-pro | 127 | $9.47 | |
| kimi-k3 | Kimi | 123 | $15.40 |
| Muse Spark 1.2 | Meta | 122 | $4.19 |
| grok-4.5 | xAI | 122 | $9.47 |
| GLM-5.3-Flash | Z.ai | 121 | $4.99 |