- Organizations
- Qwen
- Qwen4-Max
Qwen4-Max: Benchmarks, Pricing & Context Window
Qwen4-Max is a language model from Qwen, released in November 2026, with multimodal input, a 984K-token context window, and pricing from $1.50/M input, $0.075/M cached input, $4.50/M output.
Qwen4-Max is Alibaba's next-generation flagship multimodal model in the Qwen family, generally available on 2026-11-16 (model id qwen4-max). It is a sparse mixture-of-experts model with 2.4 trillion backbone parameters, 71 billion active
Qwen4-Max benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Qwen4-Max across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Qwen4-Max holds up as conversations get longer.
Quality Tracker
Qwen4-Max Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
Qwen4-Max pricing
Providers
Qwen4-Max starts at $1.50 per million input tokens and $4.50 per million output tokens via QwenCloud. Reused prompt prefixes cost $0.0750 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
| $1.50 | $0.0750 | $4.50 | 983.6K/262.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Qwen4-Max context window
Input and output token limits for Qwen4-Max, plus how it ranks on long-context understanding.
Try now
Make it with
Qwen4-Max.
Qwen4-Max latency
Qwen4-Max time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Qwen4-Max examples
Recent arena outputs from Qwen4-Max, picked from the highest-ranked matchups.
Qwen4-Max license
Qwen4-Max is a proprietary model available under its provider's product and API terms, has 2.4T parameters.
- License
- Proprietary
- Hosted access
- Parameters
- 2.4T
Proprietary license - usage restrictions apply
Qwen4-Max resources
Official sources for Qwen4-Max: provider documentation, official playground, official launch post.
Qwen4-Max vs other models
The most-compared alternatives to Qwen4-Max are GLM-5.1, Muse Spark 1.3, GPT-5.5. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen4-Max
Models ranked just above and below Qwen4-Max by LLM Stats score.
FAQ
Common questions about Qwen4-Max.