Flash — fastest and cheapest, lighter reasoningOpen Weights

Qwen Plus 0728 (thinking) Pricing

Qwen · qwen-qwen-plus-2025-07-28-thinking

Input / 1M tokens

$0.260

Output / 1M tokens

$0.780

Context window

1M tokens

≈ 1,333 pages of text

Max output

32,768 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0006

1,000 requests / month$0.624/mo 10,000 requests / month$6.24/mo 100,000 requests / month$62.40/mo

Estimate your own workloadOpens the calculator with Qwen Plus 0728 (thinking) preloaded — adjust volume and token counts there.

Price history

Only one price point recorded so far.

The staircase chart appears once a price change is detected.

Pricing and specs for this model are auto-synced from OpenRouter, but it isn't one of our editorial picks yet — no “what it excels at” write-up or business tradeoff notes. Any tier badge above is estimated from price.

Cheaper from Qwen

Qwen3.5-9BQwen$0.0002/ typical request Qwen3.6 35B A3BQwen$0.0006/ typical request

Same tier from other providers

GPT-5.4 NanoOpenAI$0.0007/ typical request Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request

Head-to-head

Qwen Plus 0728 (thinking) vs GPT-5.4 Nano →Qwen Plus 0728 (thinking) vs Claude Haiku 4.5 →Qwen Plus 0728 (thinking) vs Gemini 3.5 Flash →

Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.