GPT-4o Mini
GPT-4o MiniAlternatives?
CheaperClaude Haiku 5.5max×10.6-24%$0.21Remove sampling parameters+5BetterGPT-6 Lunalow×4.8-24%$0.005Function calling only with none · Chat Completions+3
OpenMiMo v2.6 Prothinking×11.8+107%$0.13Pass back reasoning_content+3
CheaperGLM 5.3 FlashmaxOpen×9.5-10%$0.28Defaults to max · Self-hosted+4
CheaperQwen3.8 FlashthinkingOpen×9.1-12%$0.37max_tokens range · QwenCloud+5Claude Haiku 5.5max×10.6-24%$0.21Remove sampling parameters+5GLM 5.3 FlashmaxOpen×9.5-10%$0.28Defaults to max · Self-hosted+4GPT-6 Lunamax×9.2-24%$0.068Function calling only with none · Chat Completions+3Qwen3.8 FlashthinkingOpen×9.1-12%$0.37max_tokens range · QwenCloud+5
Agnes 2.5 Pro Beta×8.9-43%$0.10 / $0.30GPT-6 Lunalow×4.8-24%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+58%-80%$0.006No image inputGPT-5.6 Lunalow×4.7+71%$0.01GPT OSS 20BhighOpen×2.6-86%$0.011No image input
Mistral Small 4thinkingOpen×2.4same$0.015MiMo v2.6 ProthinkingOpen×11.8+107%$0.13Pass back reasoning_content+3
Kimi K3maxOpen×11.2+2,186%$2.00Sampling parameters are fixed+3
Step 5 PreviewthinkingOpen×11.1+443%$1.03No web search+3
Muse Spark OpenxhighOpen×10.4+662%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1
DeepSeek V4.1 Flash 1017maxOpen×10.3+100%$0.26Pass back reasoning_content · Chat Completions+4GPT-6 Astramedium×12.6—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium×11.9—$0.21Remove unsupported parameters+5GPT-5.3 Codexxhigh×10.1—$1.75 / $14DeprecatedGPT-5.5medium×10.1—$0.90Prompts with >272K input tokensGPT-5.6 Solmedium×10.1—$0.50GPT-6 Solmedium×9.8—$0.25GPT-5.6 Terramedium×7.9—$0.18Prompts with >272K input tokensGPT-6 Lunamedium×6.7—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
7 versionsBenchmarks
in Chat & KnowledgeFAQ
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 LFM2 24B A2B?›
On Humanity's Last Exam, GPT-4o Mini scores 4.2 vs 4.2 — 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).