← All models
Balanced — strong quality at a mid priceOpen Weights
Qwen3 Next 80B A3B Thinking Pricing
Qwen · qwen-qwen3-next-80b-a3b-thinking
Input / 1M tokens
$0.150
Output / 1M tokens
$1.20
Context window
262,144 tokens
≈ 350 pages of text
Max output
32,768 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0007
1,000 requests / month$0.66/mo10,000 requests / month$6.60/mo100,000 requests / month$66.00/moEstimate your own workloadOpens the calculator with Qwen3 Next 80B A3B Thinking preloaded — adjust volume and token counts there.
Price history
List price per 1M tokens since we started tracking in Jun 2026. Each step marks a price change — hover a point for the exact date and rate.
What it excels at
Handles extended context up to 262k tokens with strong performance on structured reasoning and multi-step tasks.
The business tradeoff
Output tokens are priced eight times higher than input; quality depends on the specific open-weights deployment and quantization chosen by the host.
Cheaper from Qwen
Head-to-head
Vendor list rates, as of Jul 28, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.