Qwen2.5 7B Instruct

Provider: Alibaba (Qwen) CN

No longer listed on OpenRouter since 2026-11-12. The figures below are the last recorded values.
Input price
$0.10
/ 1M tokens
Output price
$0.20
/ 1M tokens
Context
33K tokens
Max output 29K tokens

Overview

Alibaba's Qwen2.5 7B Instruct is a budget model intended for general instruction workloads.

Strengths

  • Input priced at $0.1 per million tokens
  • Output priced at $0.2 per million tokens
  • Supports structured JSON mode
  • Includes native function-calling capability

Best use cases

  • Low-cost automated text summarization pipelines
  • Budget-constrained JSON data extraction tasks
  • Simple function-calling integration workflows

Pricing position

Matches the $0.1 input price of GPT-5.4 Nano and Llama 4 Scout, while output matches Qwen3.6 35B A3B at $0.2.

Caveats

Context is limited to 32768 tokens, significantly lower than the 1M+ token windows of newer models like Qwen3.7 Flash.

Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.

Key facts

Price basis
Median third-party host price (no first-party API)
Max output
29K tokens
Knowledge cutoff
2024-06-30
Listed on OpenRouter
2024-10-16
Tracked since
2026-05-08
Last updated
2026-11-12

Features

Function callingJSON output

Price history

  • 2026-11-12 No longer listed

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.02
1M (small app) 1 0.5 $0.20
10M (mid scale) 10 5 $2.00
100M (large) 100 50 $20.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Alibaba (Qwen)

Similar-priced models

Source: OpenRouter API (qwen/qwen-2.5-7b-instruct)