qwen Open weights Vision

Qwen2.5 VL 72B Instruct pricing & benchmarks

Released Feb 1, 2025 · served by 2 providers

Input / 1M tokens$0.250
Output / 1M tokens$0.750
Context window128K
Cached input$0.400
1M in + 300K out$0.47

What Qwen2.5 VL 72B Instruct is

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.

Providers and prices for Qwen2.5 VL 72B Instruct

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Nebiuscheapest $0.250 $0.750 32K fp8 98.0%
Parasail $0.800 $1.00 128K fp8 99.3%

FAQ

How much does the Qwen2.5 VL 72B Instruct API cost?

$0.250 per 1M input tokens and $0.750 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.47.

Is Qwen2.5 VL 72B Instruct free?

No. It is a paid model starting at $0.250 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen2.5 VL 72B Instruct?

Nebius at $0.250 input / $0.750 output per 1M tokens (fp8 quantization).

Can I self-host Qwen2.5 VL 72B Instruct?

Yes — weights are published as Qwen/Qwen2.5-VL-72B-Instruct on Hugging Face, so you can run it on your own hardware.