← All models
Balanced — strong quality at a mid priceOpen Weights
Qwen2.5 72B Instruct Pricing
Qwen · qwen-qwen-2-5-72b-instruct
Input / 1M tokens
$0.360
Output / 1M tokens
$0.400
Context window
32,768 tokens
≈ 44 pages of text
Max output
16,384 tokens
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0006
1,000 requests / month$0.592/mo10,000 requests / month$5.92/mo100,000 requests / month$59.20/moEstimate your own workloadOpens the calculator with Qwen2.5 72B Instruct 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.
What it excels at
Strong results on coding, math, and instruction-following benchmarks. Supports 128k context for long-document and multi-turn tasks.
The business tradeoff
Open weights require self-hosted GPUs, creating variable latency and operational overhead. Smaller ecosystem and tooling than closed frontier providers.
Cheaper from Qwen
Head-to-head
Vendor list rates, as of Jun 15, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.