Qwen4 Max
by Alibaba (Qwen) · qwen/qwen4-max · #316 cheapest of 457 paid models
Prices updated Nov 18, 2026, 7:52 AM UTC · refreshed nightly
Qwen4 Max is the flagship model in Alibaba's Qwen4 series. It accepts text, image, and video input and returns text, with a 1M-token context window and reasoning enabled by default....
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$1.42
per 1M tokens
Output
$4.27
per 1M tokens
Blended (3:1)
$2.14
3 input : 1 output
Cache read
$0.071
per 1M cached tokens
Cache write
$1.78
per 1M tokens
Cache & batch economics
Effective prices for Qwen4 Max with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.14 | $0.1496 | — |
| 50% | $1.63 | $0.0819 | −45% |
| 90% | $1.22 | $0.0278 | −81% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.001995 | $1.99 |
| Document summary | 8,000 | 1,000 | $0.0157 | $15.67 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0513 | $51.30 |
| Long-context analysis | 150,000 | 5,000 | $0.2351 | $235.12 |
Specs
Context window
1M
tokens
Max output
131K
tokens
Input modalities
text, image, video
Tokenizer
Qwen