ZMIME
Alibaba (Qwen) · Released Sep 19, 2024

Qwen2.5 7B Instruct

Small open Qwen2.5 instruction model for chat, structured output, and tool use.

  • Open weights
  • Tool calling
Capability
—No ECI score yet
Input
$0.075per 1M tokens
Output
$0.15per 1M tokens
Context
131K8K max output
Pricing

What it costs

Input
$0.075per million tokens
Output
$0.15per million tokens
Blended (3:1)
$0.094cheaper than 91% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.225
Team assistant25M input + 5M output tokens$2.63
Production app250M input + 50M output tokens$26.25

Median of 4 paid API providers on models.dev.

Capability

Independent benchmarks

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

  • GPQA DiamondGraduate-level science questions35.5%
  • OTIS Mock AIME 2024–2025Competition mathematics2.5%

Scores from Epoch AI, run independently of Alibaba (Qwen).

Specifications

The details

Lab
Alibaba (Qwen)
Released
Sep 19, 2024
Context window
131,072 tokens
Max output
8,192 tokens
Inputs
Text
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
No
Availability
5 API providerslisted on models.dev
Same lab

More from Alibaba (Qwen)

Questions

About Qwen2.5 7B Instruct

How much does Qwen2.5 7B Instruct cost?

Qwen2.5 7B Instruct costs $0.075 input / $0.15 output per million tokens (median across 4 API providers). At a 3:1 input-to-output mix that is $0.094 per million tokens, cheaper than 91% of the 469 priced models we track.

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

Qwen2.5 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 7B Instruct?

Epoch AI has not published a Capabilities Index score for Qwen2.5 7B Instruct yet. Epoch AI benchmark results: GPQA Diamond 35.5%, OTIS Mock AIME 2024–2025 2.5%.

Is Qwen2.5 7B Instruct open source?

Yes. Alibaba (Qwen) publishes the weights under the Apache 2.0 licence, so it can be downloaded and self-hosted.

What inputs does Qwen2.5 7B Instruct support?

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

When was Qwen2.5 7B Instruct released?

Alibaba (Qwen) released Qwen2.5 7B Instruct on Sep 19, 2024.

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

The closest current models from other labs on capability, price and release date are Mistral Nemo (Mistral AI, ECI 113.8, $0.09 / $0.109), GPT-4o mini (OpenAI, ECI 123.8, $0.15 / $0.60), Gemma 3 12B IT (Google, $0.05 / $0.15) and Claude Haiku 3 (Anthropic, ECI 117.8, $0.25 / $1.25).