Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
Qwen

Qwen2.5 72B

Legacy$Affordable
Qwen#65 of 92
CompareChat

Large 72B model from the Qwen 2.5 generation. Strong multilingual reasoning and instruction following. Superseded by Qwen3 series.

▼

Qwen2.5 72B by Qwen has a Capability Index of 62.8, making it below the field average in capability. It ranks #65 out of 92 models on the idapt capability leaderboard. Qwen2.5 72B is somewhat expensive at $0.36/M tokens input and $0.40/M tokens output. The model supports a 33K context window.

Best forFrontier reasoningCost-effective
Replaced by
QwenQwen3 235B A22B
See the full deprecation timeline

Benchmarks

CodingInsufficient data
AgenticInsufficient data
Sources:Epoch ECI·Epoch AI·OpenRouter· as of 2026-07-10

Category Rankings

Capability
#65of 92
Math
#52of 70
Reasoning
#60of 78

Specifications

Vision
Audio
Reasoning
Dense
Architecture
72B
Parameters
33K
Context
16K
Max output

Performance

Providers

Misc

September 19, 2024
Released
Same family
QwenQwen2.5 VL 32BQwenQwen2.5 VL 72BQwenQwen2.5 7BQwenQwen2.5 Coder 32BQwenQwen2.5 Coder 7BQwenQwen2.5 VL 7B
CompareChat with Qwen2.5 72B

Compare with

OpenAIGPT 5.6 Solvs Qwen2.5 72BOpenAIGPT 5.6 Lunavs Qwen2.5 72BAnthropicClaude Fable 5vs Qwen2.5 72BAnthropicClaude Opus 4.8vs Qwen2.5 72BAnthropicClaude Sonnet 5vs Qwen2.5 72BAnthropicClaude Haiku 4.5vs Qwen2.5 72BGoogleGemini 3.6 Flashvs Qwen2.5 72BGoogleGemini 3.5 Flashvs Qwen2.5 72BGoogleGemini 3.5 Flash-Litevs Qwen2.5 72BGoogleGemma 4 31Bvs Qwen2.5 72BxAIGrok 4.5vs Qwen2.5 72BxAIGrok Build 0.1vs Qwen2.5 72BxAIGrok 4.1 Fastvs Qwen2.5 72BMetaMuse Spark 1.1vs Qwen2.5 72BDeepSeekDeepSeek V4 Provs Qwen2.5 72BDeepSeekDeepSeek V4 Flashvs Qwen2.5 72BMiniMaxMiniMax M3vs Qwen2.5 72BMoonshotAIKimi K3vs Qwen2.5 72BMoonshotAIKimi K2.7 Codevs Qwen2.5 72BZhipu AIGLM 5.2vs Qwen2.5 72BQwenQwen3.7 Maxvs Qwen2.5 72BQwenQwen3.7 Plusvs Qwen2.5 72BQwenQwen3 Coder Nextvs Qwen2.5 72BNVIDIANemotron 3 Ultravs Qwen2.5 72BMistral AIMistral Small 4vs Qwen2.5 72B
Frequently Asked Questions about Qwen2.5 72B▼

When was Qwen2.5 72B released?

▼

Qwen2.5 72B was released on September 19, 2024.

Who created Qwen2.5 72B?

▼

Qwen2.5 72B was created by Qwen.

How capable is Qwen2.5 72B?

▼

Qwen2.5 72B has a Capability Index of 62.8/100, making it below the field average in capability. It ranks #65 out of 92 models.

How much does Qwen2.5 72B cost?

▼

Qwen2.5 72B costs $0.36/M input tokens and $0.40/M output tokens.

What is Qwen2.5 72B API pricing?

▼

The Qwen2.5 72B API is priced at $0.36 per million input tokens and $0.40 per million output tokens. You can access Qwen2.5 72B through idapt.app alongside 200+ other AI models in one workspace.

Is Qwen2.5 72B a reasoning model?

▼

No, Qwen2.5 72B is not a reasoning model. It responds directly without an extended internal thinking step. For tasks requiring deep chain-of-thought reasoning, consider models like Claude, o-series from OpenAI, or Gemini Thinking.

Does Qwen2.5 72B support image or vision input?

▼

No, Qwen2.5 72B does not currently support image or vision input. It is a text-only model.

Does Qwen2.5 72B support audio?

▼

No, Qwen2.5 72B does not support audio input.

What is the context window of Qwen2.5 72B?

▼

Qwen2.5 72B has a context window of 33K tokens, meaning it can process approximately 24,576 words of context at once.

Is Qwen2.5 72B open source?

▼

Qwen2.5 72B is a proprietary model developed by Qwen. The model weights and training data are not publicly available.

Where can I use Qwen2.5 72B?

▼

You can chat with Qwen2.5 72B on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access Qwen2.5 72B through Qwen's own API or platform.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Credentials
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • idapt Code
  • Code Execution
  • Computers
  • Computer Use
  • Computer Assist · Soon
  • Containers · Soon
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • LLM cost calculator
  • Token counter
  • Context window checker
  • Can I run it
  • Model picker quiz
  • Savings finder
  • Video cost estimator
  • Text to speech cost
  • Transcription cost
  • API endpoint tester
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Skills
  • Learn
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)