o4 Mini
Apr 2025
Retired 2026-10-23Replace withGPT-5.6 TerraNewer version
MiMo v2.6 ProCheaper, as goodGPT-6 LunaBetter
GPT-5.6 TerraNewer versionMiMo v2.6 ProCheaper, as goodGPT-6 LunaBettero4 MiniCompare inon
Benchmarks of o4 Mini39
BenchmarkByScoreRank
Overall1
Knowledge6
Reasoning4
Math7
Science2
Coding1
Multimodal3
Writing2
Health & law3
Documents1
Legacy · saturated or no longer reported9
No benchmark matches
Rankingat high effort?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen×2.8-72%$0.13Pass back reasoning_content+3BetterGPT-6 Lunalow+29%-90%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×2.7-73%$0.26Pass back reasoning_content · Chat Completions+4
CheaperStep 5 PreviewthinkingOpen×2.6-26%$1.03web_search not available · Chat Completions+2
CheaperClaude Haiku 5.5max×2.6-90%$0.21Remove sampling parameters+5ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×2.8-72%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×2.7-73%$0.26Pass back reasoning_content · Chat Completions+4Step 5 PreviewthinkingOpen×2.6-26%$1.03web_search not available · Chat Completions+2Claude Haiku 5.5max×2.6-90%$0.21Remove sampling parameters+5
MiniMax M3.1 Flashthinking×2.6-86%$0.22Complete model response must be appendedModelScoreCostPer taskWhat changes
GPT-6 Lunalow+29%-90%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+26%-77%$0.01MiMo v2.5thinkingOpen+31%-91%$0.019Claude Haiku 5.5low+77%-90%$0.024Remove sampling parameters+5MiMo v2.5 ProthinkingOpen+56%-72%$0.054No image inputModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×2.8-72%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×2.7-73%$0.26Pass back reasoning_content · Chat Completions+4
GLM 5.3maxOpen×2.7+12%$2.01No image input+4Step 5 PreviewthinkingOpen×2.6-26%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×2.6+212%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astrahigh×3.1—$1.73Monitoring can return HTTP 403+2GPT-6.1 Solhigh×3—$0.32Remove unsupported parameters+5GPT-6 Solhigh×2.5—$0.37GPT-5.6 Solhigh×2.5—$0.81GPT-5.5high×2.2—$1.54Prompts with >272K input tokensGPT-5.6 Terrahigh×2.1—$0.34Prompts with >272K input tokensGPT-6 Lunahigh+98%—$0.029Function calling only with none · Chat Completions+3GPT-5.3 Codexxhigh+95%—$1.75 / $14DeprecatedAll OpenAI models →History
3 versionsBenchmarks
all categoriesChat & Knowledge
AA Omniscience Index-35.7
GPQA Diamond78.4
Coding
Agents & Tool Use
τ²-bench · AA55.6
Writing & Language
Vision & Documents
FAQ
How much does o4 Mini cost?›
$1.10 per 1M input tokens and $4.40 per 1M output tokens; cached input $0.28 per 1M.
Is o4 Mini free to use?›
There is no free API; the cheapest paid price is $1.10 per 1M input tokens.
How can I use o4 Mini?›
Through the API of OpenAI.
What is the context window of o4 Mini?›
200K tokens, with up to 100K output tokens.
When was o4 Mini released? Is there a newer version?›
Released 2025-04-16. It has been superseded by GPT-5.6 Terra.
Is o4 Mini open source?›
No, o4 Mini is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can o4 Mini read images?›
It accepts text and images, PDF files as input.
What is o4 Mini?›
o4 Mini is a closed language model from OpenAI, released Apr 2025, the successor to o1 Mini.
What are the best alternatives to o4 Mini?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).