All AI models · LLM benchmarks · Methodology

Alibaba

Qwen 3 Max Thinking

Qwen reasoning model for deliberate problem solving, math, and coding

Model facts

Context window
256K tokens
Maximum output
66K tokens
Cheapest paid input
$0.78 per 1M tokens
Cheapest paid output
$3.9 per 1M tokens
Open weights
yes
Providers
4

Capabilities and modalities

reasoning, tool calling, structured output, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default32.5not measurednot measurednot measured
Preview25.5not measured82.3not measured

Observed price history

  • 2026-08-24: $0.78 input / $3.9 output per 1M tokens

API providers

  • OpenRouter — model id qwen/qwen3-max-thinking; $0.78 input / $3.9 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id alibaba/qwen3-max-thinking; $1.2 input / $6 output per 1M tokens; provider documentation
  • ZenMux — model id qwen/qwen3-max; $1.2 input / $6 output per 1M tokens; provider documentation
  • Arena — model id qwen3-max-thinking; not published input / not published output per 1M tokens; provider documentation