# Qwen3 Max Usage, Cost & Rank | OpenCode Data

> Qwen3 Max costs $1.20 per 1M input tokens and $6.00 per 1M output tokens.

Flagship Qwen3 model for coding agents, complex reasoning, and tool use

- Page: https://opencode.ai/data/alibaba/qwen3-max
- JSON: https://opencode.ai/data/alibaba/qwen3-max.json
- Model ID: alibaba/qwen3-max
- Lab: Alibaba

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 262K |
| Max output | 66K |
| Knowledge cutoff | 2025-04 |
| Release date | 2025-09-23 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | No |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $1.20 | $6.00 | $0.24 | - |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| Artificial Analysis Coding Index | 26.4 | index | https://openrouter.ai/qwen/qwen3-max/benchmarks |
| SciCode | 38.3 | percent correct | https://openrouter.ai/qwen/qwen3-max/benchmarks |
| Terminal-Bench Hard | 20.5 | success rate | https://openrouter.ai/qwen/qwen3-max/benchmarks |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.