/ Models

Language models

Qwen: Qwen2.5 VL 72B Instruct

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.

Maker
Qwen
Context window
128K
Max output
128K
Input / 1M
$0.8
Output / 1M
$1
1M in + 1M out
$1.80

Everything else

Max output128K
Input / 1M$0.8
Output / 1M$1
Cache read / 1M$0.4
Cache write / 1M
1M in + 1M out$1.80
Takestext, image
Returnstext
Toolsno
Reasoningno
Open weightsyes
Released2025-02-01
Knowledge cutoff2024-06-30
Retires
Catalog idqwen/qwen2.5-vl-72b-instruct

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models