Qwen

Qwen2.5 VL 72B Instruct

qwen/qwen2.5-vl-72b-instruct
Model weightsReleased Feb 1, 2025Open Weights
Visionopen weights

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.

Cost / 1M tokens

Low usage

$0.80

input

$0.40

cached input

$1.00

output

Context Window

128K

Up to 115K max output

Modalities

text, image → text

Qwen tokenizer

Quickstart & API

qwen/qwen2.5-vl-72b-instruct
Open the model picker in ChatOSS Desktop (Code, Kanban, or Chat) and select or paste this model ID.

Best for & Strengths

Key Strengths

Open weightsMultimodal vision

Recommended Workloads in ChatOSS

  • Screenshot-to-code workflows
  • Open-source AI workflows
Available in ChatOSS Code, Kanban Orchestrate, and Chat modes via Plus, Max, or BYOK.

Active Provider Endpoints (1)

Upstream inference providers serving Qwen2.5 VL 72B Instruct, with per-provider pricing, context limits, quantization, and 24-hour uptime.

ProviderInput / 1MOutput / 1MCache Read / 1MContextMax OutputQuantizationUptime (24h)
Parasailcache
parasail/fp8
$0.80$1.00$0.40128K115Kfp899.9%

Supported API Parameters

Parameters accepted by this model when called through ChatOSS or OpenRouter.

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_logprobstop_p

Compare Similar Models

Browse all models →