Qwen2.5 VL 72B Instruct pricing & benchmarks
Qwen2.5 VL 72B Instruct is available from Alibaba at $0.250 per million input tokens and $0.750 per million output tokens ($0.375 blended at 3:1). It accepts up to 128,000 tokens of context. Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Pricing
Per million tokens · OpenRouter
Input$0.250
Output$0.750
Blended (3:1)$0.375
Specification
qwen/qwen2.5-vl-72b-instruct
Context window128K
Max output—
ReleasedFeb 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for Qwen2.5 VL 72B Instruct yet. We show nothing rather than reprinting an unverified figure.
Where to run Qwen2.5 VL 72B Instruct
2 hosts · 2.3× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Weights | Uptime 24h |
|---|---|---|---|---|---|
| Nebius ⚠ 32K context, not 128K |
$0.375 | $0.250 / $0.750 | 32K | fp8 | 99.3% |
| Parasail | $0.850 | $0.800 / $1.00 | 128K | fp8 | 99.3% |
Host prices and uptime from OpenRouter, synced 2026-08-08. Lower-precision weights (fp4, fp8) can cost less and score worse than the same model at bf16 — the score above is not host-specific.
Compare Qwen2.5 VL 72B Instruct
Qwen2.5 VL 72B Instruct vs DeepSeek V4 Flash 0731
Qwen2.5 VL 72B Instruct vs Claude Opus 5
Qwen2.5 VL 72B Instruct vs Gemini 3.6 Flash
Qwen2.5 VL 72B Instruct vs Kimi K3
Qwen2.5 VL 72B Instruct vs GPT-5.6 Luna
Qwen2.5 VL 72B Instruct vs GPT-5.6 Terra
Qwen2.5 VL 72B Instruct vs GPT-5.6 Sol
Qwen2.5 VL 72B Instruct vs Grok 4.5
FAQ
How much does Qwen2.5 VL 72B Instruct cost?
Qwen2.5 VL 72B Instruct costs $0.250 per million input tokens and $0.750 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.375 per million tokens.
What is Qwen2.5 VL 72B Instruct's context window?
Qwen2.5 VL 72B Instruct accepts up to 128,000 tokens of context.