GPT-4o Mini
GPT-4o MiniRankingin non-thinking mode?
Alternatives?
CheaperClaude Haiku 5.5max×6.5-24%$0.21Remove sampling parameters+5BetterGPT-6 Lunalow×3.2-24%$0.005Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking×7+107%$0.13Pass back reasoning_content+3
CheaperGLM 5.3 FlashmaxOpen×6.3-10%$0.28Defaults to max · Self-hosted+4
CheaperQwen3.8 FlashthinkingOpen×6-12%$0.37max_tokens range · QwenCloud+5Claude Haiku 5.5max×6.5-24%$0.21Remove sampling parameters+5GLM 5.3 FlashmaxOpen×6.3-10%$0.28Defaults to max · Self-hosted+4Qwen3.8 FlashthinkingOpen×6-12%$0.37max_tokens range · QwenCloud+5GPT-6 Lunamax×5.7-24%$0.068Function calling only with none · Chat Completions+3MiMo v2.6 FlashthinkingOpen×5.7-33%$0.062Pass back reasoning_content+3GPT-6 Lunalow×3.2-24%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+36%-80%$0.006No image input
Gemma 4 E4BthinkingOpen+34%-85%$0.008GPT-5.6 Lunalow×3.2+71%$0.01GPT OSS 20BhighOpen+35%-86%$0.011No image inputMiMo v2.6 ProthinkingOpen×7+107%$0.13Pass back reasoning_content+3
DeepSeek V4.1 Flash 1017maxOpen×6.8+100%$0.26Pass back reasoning_content · Chat Completions+4GLM 5.3maxOpen×6.7+719%$2.01No image input+4
Step 5 PreviewthinkingOpen×6.6+443%$1.03No web search+3
Kimi K3maxOpen×6.5+2,186%$2.00Sampling parameters are fixed+3GPT-6 Astramedium×7.4—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium×7.2—$0.21Remove unsupported parameters+5GPT-6 Solmedium×6—$0.25GPT-5.6 Solmedium×5.9—$0.50GPT-5.5medium×5.1—$0.90Prompts with >272K input tokensGPT-5.3 Codexxhigh×4.9—$1.75 / $14DeprecatedGPT-5.6 Terramedium×4.5—$0.18Prompts with >272K input tokensGPT-6 Lunamedium×4.5—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
7 versionsBenchmarks
all categoriesFAQ
How much does GPT-4o Mini cost?›
$0.15 per 1M input tokens and $0.60 per 1M output tokens; cached input $0.075 per 1M.
Is GPT-4o Mini free to use?›
There is no free API; the cheapest paid price is $0.15 per 1M input tokens.
How good is GPT-4o Mini, and what is it best at?›
#301 of 334 in Chat & Knowledge, #135 of 156 in Coding, #122 of 175 in Agents & Tool Use, #133 of 195 in Writing & Language, #118 of 124 in Vision & Documents.
Is GPT-4o Mini better than Mistral Small 3?›
On AA Intelligence Index 4.3.2, GPT-4o Mini scores 6.7 vs 6.7 — about the same.
How can I use GPT-4o Mini?›
Through the API of Azure, OpenAI.
What is the context window of GPT-4o Mini?›
128K tokens, with up to 16K output tokens.
When was GPT-4o Mini released? Is there a newer version?›
Released 2024-07-18. It has been superseded by GPT-5 Mini.
Is GPT-4o Mini open source?›
No, GPT-4o Mini is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-4o Mini read images?›
It accepts text and images, PDF files as input.
What is GPT-4o Mini?›
GPT-4o Mini is a closed language model from OpenAI, released Jul 2024.
What are the best alternatives to GPT-4o Mini?›
Claude Haiku 5.5 (cheaper), GPT-6 Luna (better), MiMo v2.6 Pro (open weights).