Qwen: Qwen4 Max
Qwen4 Max is a model from Qwen that accepts text, image, and video inputs and returns text. It offers a context window of 1,000,000 tokens and can generate up to 131,072 tokens in a single completion, which suits long documents, large codebases, or lengthy multimodal inputs. It supports tool calling and a reasoning mode. Structured output support is not specified, so teams that depend on strict schema adherence should test it directly. Pricing is $1.425 per million input tokens and $4.275 per million output tokens; it is not offered free. Buyers who need very long context, video input, and tool use at that rate should shortlist it. There is no independent benchmark coverage yet, so its quality relative to alternatives is unproven. Run your own evaluations on representative tasks before committing production workloads, and compare results against models with published scores.
- Model ID
- qwen/qwen4-max
- Vendor
- qwen
- Released
- November 2026
- Tokenizer
- Qwen
- Input Modalities
- text, image, video
- Output Modalities
- text
- Max Output
- 131,072 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $1.43/M input and $4.28/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | $0.05 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.93 |
| A month of a busy support chatbot | 5M in / 2M out | $15.68 |
Price & spec history
Tracked daily by PicksByModel since 2026-11-16.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-11-17 | $1.43 | $4.28 | 1,000,000 |
| 2026-11-16 | $1.50 | $4.50 | 1,000,000 |
Similar models
Qwen: Qwen3.8 Max Prime
Qwen: Qwen3.8 Omni Flash
Qwen: Qwen3.8 Max (0902)
Qwen: Qwen3.8 Max (0902) (batch)
Qwen: Qwen3.8 Flash
Qwen: Qwen3.8 27B
Quick answers
- How much does Qwen: Qwen4 Max cost?
- $1.43 per million input tokens and $4.28 per million output tokens.
- What is Qwen: Qwen4 Max's context window?
- 1,000,000 tokens, roughly 1,500 pages of text in a single request.
- Does Qwen: Qwen4 Max support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Qwen: Qwen4 Max process images?
- Yes, it accepts image input.