impulse

Qwen2 VL 72B Instruct

Open weights
API id Qwen2-VL-72B-Instruct
Input / 1M
$0.13
at Nebius AI Studio
Output / 1M
$0.40
at Nebius AI Studio
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at Nebius AI Studio, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.13$0.40

What it costs a month

At Nebius AI Studio list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$69.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$76.80
  • Coding agent1,000 requests a day, 40K in / 2K out$180
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$408
Use your own numbers

Where to run it

2 hosts serve Qwen2 VL 72B Instruct. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
Qwen2-VL-72B-Instruct
$0.13 / $0.40
Fireworks AIInference
qwen2-vl-72b-instruct
$0.90 / $0.90
+356% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, SGLang, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Nebius AI Studio.

Smaller Alibaba Qwen models

No cheaper Alibaba Qwen model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Qwen3.8 Flash
    Alibaba Qwen · on AIHubMix
    $0.113 / $0.38
    Has every key capability
    9% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    9% less
  • Gemma 4 31B IT
    Google · on W&B Inference
    $0.10 / $0.34
    Has every key capability
    19% less
  • Ministral 8B 2512
    Mistral AI · on Mistral AI
    $0.15 / $0.15
    Has every key capability
    24% less

Model line

Newer and older versions, at each lab's own price.

  1. Feb 2025Qwen2.5 VL 72B InstructLatest$0.25 / $0.75
  2. UndatedQwen2 VL 72B InstructThis page$0.13 / $0.40

Call it

Using Nebius AI Studio's API.

Python
from litellm import completion

response = completion(
    model="nebius/Qwen2-VL-72B-Instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Qwen2 VL 72B Instruct cost?

On Nebius AI Studio, Qwen2 VL 72B Instruct costs $0.13 per million input tokens and $0.40 per million output tokens.

Which APIs offer Qwen2 VL 72B Instruct?

Qwen2 VL 72B Instruct runs on 2 APIs: Nebius AI Studio and Fireworks AI.

What is Qwen2 VL 72B Instruct's context window?

131K tokens, with up to 131K tokens in one reply.

Is Qwen2 VL 72B Instruct being retired?

No retirement date is scheduled for it on any API we track.

Is there a newer version of Qwen2 VL 72B Instruct?

Yes. Qwen2.5 VL 72B Instruct is the newest model in this line, released on 1 Feb 2025.

What are cheaper alternatives to Qwen2 VL 72B Instruct?

Models that cost less and keep most of what it can do: Qwen3.8 Flash on AIHubMix (9% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Qwen2 VL 72B Instruct's API model id?

Use Qwen2-VL-72B-Instruct with Nebius AI Studio. Other hosts use their own ids: qwen2-vl-72b-instruct on Fireworks AI.

Sources

Raw catalog entry for Qwen2-VL-72B-Instruct on Nebius AI Studio
{
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "input_cost_per_token": 1.3e-7,
  "output_cost_per_token": 4e-7,
  "litellm_provider": "nebius",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_vision": true,
  "source": "https://nebius.com/prices"
}