ZMIME
Alibaba (Qwen) · Released Sep 2024

Qwen2.5-VL 7B Instruct

Qwen vision-language model for visual reasoning, documents, and agent tasks.

  • Open weights
  • Tool calling
  • Vision
  • Retired
Capability
—No ECI score yet
Input
$0.35per 1M tokens
Output
$1.05per 1M tokens
Context
131K8K max output

Retired Qwen2.5-VL 7B Instruct is no longer offered by Alibaba (Qwen) or any API host we track (since Nov 2, 2026). The specs and prices below are its last published listing, kept for reference.

Pricing

What it costs

Input
$0.35per million tokens
Output
$1.05per million tokens
Blended (3:1)
$0.525cheaper than 56% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$1.23
Team assistant25M input + 5M output tokens$14.00
Production app250M input + 50M output tokens$140.00

Official Alibaba API price, as listed on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Qwen2.5-VL 7B Instruct yet.

Specifications

The details

Lab
Alibaba (Qwen)
Released
Sep 2024
Knowledge cutoff
Apr 2024
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text, Images
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
No
Weights
Open weights
API model ID
qwen2-5-vl-7b-instructon Alibaba
Availability
1 API providerlisted on models.dev
Status
Retired no provider has listed it since Nov 2, 2026

Alibaba model documentation

Same lab

More from Alibaba (Qwen)

Questions

About Qwen2.5-VL 7B Instruct

Is Qwen2.5-VL 7B Instruct still available?

No. Qwen2.5-VL 7B Instruct has been retired: neither Alibaba (Qwen) nor any API host we track lists it since Nov 2, 2026. This page keeps its last published specs and prices for reference.

How much does Qwen2.5-VL 7B Instruct cost?

Qwen2.5-VL 7B Instruct costs $0.35 input / $1.05 output per million tokens (official Alibaba API price). At a 3:1 input-to-output mix that is $0.525 per million tokens, cheaper than 56% of the 469 priced models we track.

What is the context window of Qwen2.5-VL 7B Instruct?

Qwen2.5-VL 7B Instruct accepts up to 131,072 tokens per request and can write up to 8,192 tokens in one response.

How good is Qwen2.5-VL 7B Instruct?

Epoch AI has not published a Capabilities Index score for Qwen2.5-VL 7B Instruct yet.

Is Qwen2.5-VL 7B Instruct open source?

Yes. Alibaba (Qwen) publishes the weights, so it can be downloaded and self-hosted.

What inputs does Qwen2.5-VL 7B Instruct support?

Qwen2.5-VL 7B Instruct accepts text and images and replies in text. It is not a dedicated reasoning model, supports tool calling.

When was Qwen2.5-VL 7B Instruct released?

Alibaba (Qwen) released Qwen2.5-VL 7B Instruct on Sep 2024. Its training data runs to Apr 2024.

What are the best alternatives to Qwen2.5-VL 7B Instruct?

The closest current models from other labs on capability, price and release date are Codestral (Mistral AI, $0.30 / $0.90), Aya Expanse 32B (Cohere, $0.50 / $1.50), Llama-3.2-11B-Vision-Instruct (Meta, $0.055 / $0.345) and Llama 3.1 Nemotron 70B Instruct (NVIDIA, $0.478 / $0.504).