Qwen2.5-14B-Instruct

Name: Qwen2.5-14B-Instruct
Author: Alibaba

Released

2024-06-07

Last refreshed

2026-06-29

Status

Researched 136d ago

Open sourceCommercial use: permittedRAGLong contextClassificationJSON / Tool use

Qwen2.5-14B-Instruct is worth evaluating for rag, long context, and classification when its provider route and context window match the workload.

Use it for

Teams evaluating rag, long context, and classification
Workloads that can use a 128k context window
Buyers comparing 3 tracked provider routes

Do not use it for

Vision or document-understanding workloads

Specifications

Family: Qwen2.5
Released: 2024-06-07
Context: 128k
Parameters: 14.7B
Architecture: Decoder Only
Specialization: general
Openness: Open source
License: Apache 2.0OSI-approvedCommercial use: permitted
Weights: Available
Code: Unknown
Training: Fine-tuned

Created by

Alibaba

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China

Founded 2017

Website

Pricing

Output / 1M

$0.080

Input / 1M

$0.080

Cheapest of 3 routes · SiliconFlow

Providers(3)

DeepInfra Fireworks AI SiliconFlow

View 3 provider routes

About

Instruction-optimized 14B variant for complex queries requiring nuanced responses and strong multilingual support.

Top use-case fit

RAG

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Classification

Q/$ A

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 3

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
SiliconFlow	$0.080	$0.080	Serverless
DeepInfra	$0.100	$0.100	Serverless
Fireworks AI	$0.200	$0.200	Serverless

Available via routers & gateways(1)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughFireworks AI

Capabilities

Structured Outputs

Benchmark peer barsfor Classification

Massive Multitask Language UnderstandingRank 25 of 95

Gemini 3.1 Pro Preview

98.0

GPT-5.5

92.4

Claude Opus 4.6

91.1

DeepSeek V4 Pro

90.1

Qwen2.5-14B-Instructcurrent

84.2

Benchmark scores(1)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.