Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free
OpenAI

GPT Mini (120b)

$Affordable
OpenAI#49 of 92
CompareChat

OpenAI's budget-friendly reasoning model — fast and surprisingly capable. Sparse Mixture-of-Experts design (120B total, only 5B active per request) keeps costs low while delivering strong reasoning. Adjustable thinking depth and tool use support.

▼

GPT Mini (120b) by OpenAI has a Capability Index of 73.2, making it comparable to the field average. It ranks #49 out of 92 models on the idapt capability leaderboard. GPT Mini (120b) is somewhat expensive at $0.04/M tokens input and $0.17/M tokens output. The model supports extended reasoning, a 131K context window.

Best forFrontier reasoningCost-effective

Benchmarks

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

Category Rankings

Capability
#49of 92
Agentic
#41of 45

Specifications

Vision
Audio
Reasoning
MoE
Architecture
120B
Parameters
5B
Active
131K
Context
66K
Max output

Performance

Providers

Misc

August 5, 2025
Released
Same family
OpenAIGPT OSS 20B
CompareChat with GPT Mini (120b)

Compare with

OpenAIGPT 5.6 Solvs GPT Mini (120b)OpenAIGPT 5.6 Lunavs GPT Mini (120b)AnthropicClaude Fable 5vs GPT Mini (120b)AnthropicClaude Opus 4.8vs GPT Mini (120b)AnthropicClaude Sonnet 5vs GPT Mini (120b)AnthropicClaude Haiku 4.5vs GPT Mini (120b)GoogleGemini 3.6 Flashvs GPT Mini (120b)GoogleGemini 3.5 Flashvs GPT Mini (120b)GoogleGemini 3.5 Flash-Litevs GPT Mini (120b)GoogleGemma 4 31Bvs GPT Mini (120b)xAIGrok 4.5vs GPT Mini (120b)xAIGrok Build 0.1vs GPT Mini (120b)xAIGrok 4.1 Fastvs GPT Mini (120b)MetaMuse Spark 1.1vs GPT Mini (120b)DeepSeekDeepSeek V4 Provs GPT Mini (120b)DeepSeekDeepSeek V4 Flashvs GPT Mini (120b)MiniMaxMiniMax M3vs GPT Mini (120b)MoonshotAIKimi K3vs GPT Mini (120b)MoonshotAIKimi K2.7 Codevs GPT Mini (120b)Zhipu AIGLM 5.2vs GPT Mini (120b)QwenQwen3.7 Maxvs GPT Mini (120b)QwenQwen3.7 Plusvs GPT Mini (120b)QwenQwen3 Coder Nextvs GPT Mini (120b)NVIDIANemotron 3 Ultravs GPT Mini (120b)Mistral AIMistral Small 4vs GPT Mini (120b)
Frequently Asked Questions about GPT Mini (120b)▼

When was GPT Mini (120b) released?

▼

GPT Mini (120b) was released on August 5, 2025.

Who created GPT Mini (120b)?

▼

GPT Mini (120b) was created by OpenAI.

How capable is GPT Mini (120b)?

▼

GPT Mini (120b) has a Capability Index of 73.2/100, making it comparable to the field average. It ranks #49 out of 92 models.

How much does GPT Mini (120b) cost?

▼

GPT Mini (120b) costs $0.04/M input tokens and $0.17/M output tokens.

What is GPT Mini (120b) API pricing?

▼

The GPT Mini (120b) API is priced at $0.04 per million input tokens and $0.17 per million output tokens. You can access GPT Mini (120b) through idapt.app alongside 200+ other AI models in one workspace.

Is GPT Mini (120b) a reasoning model?

▼

Yes, GPT Mini (120b) is a reasoning model. It can think step-by-step through complex problems before providing an answer, often yielding better results on difficult tasks like math, coding, and multi-step logic.

Does GPT Mini (120b) support image or vision input?

▼

No, GPT Mini (120b) does not currently support image or vision input. It is a text-only model.

Does GPT Mini (120b) support audio?

▼

No, GPT Mini (120b) does not support audio input.

What is the context window of GPT Mini (120b)?

▼

GPT Mini (120b) has a context window of 131K tokens, meaning it can process approximately 98,304 words of context at once.

Is GPT Mini (120b) open source?

▼

GPT Mini (120b) is a proprietary model developed by OpenAI. The model weights and training data are not publicly available.

Where can I use GPT Mini (120b)?

▼

You can chat with GPT Mini (120b) on idapt.app — no separate API key required. idapt is an AI workspace with 200+ models, agents, computers, and tasks. You can also access GPT Mini (120b) through OpenAI'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)