GPT-5.4 Mini
GPT-5.4 MiniAlternatives?
CheaperGemini 3.8 Flashhigh+20%-11%*$3.49Sampling parameters are ignored+1BetterGPT-6 Lunalow+7%-88%$0.005Function calling only with none · Chat Completions+3
OpenMuse Spark Openxhigh+14%+19%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1CheaperGemini 3.6 Flashhigh+17%-11%*$1.60
CheaperDeepSeek V4.1 Flash 1017maxOpen+13%-69%$0.26Pass back reasoning_content · Chat Completions+4Gemini 3.8 Flashhigh+20%-11%*$3.49Sampling parameters are ignored+1Gemini 3.6 Flashhigh+17%-11%*$1.60DeepSeek V4.1 Flash 1017maxOpen+13%-69%$0.26Pass back reasoning_content · Chat Completions+4
Qwen3.7 Plusthinking+13%-67%$0.22Gemini 3 Flash Previewthinking+12%-33%$0.50 / $3GPT-6 Lunalow+7%-88%$0.005Function calling only with none · Chat Completions+3GPT-5.6 Lunalow+4%-73%$0.01
MiMo v2.5thinkingOpen+6%-90%$0.042GPT-6.1 Terralow+16%+19%$0.055Muse Glimmer 30BhighOpen+4%-70%$0.058Context: 400K → 131KMuse Spark OpenxhighOpen+14%+19%$0.84Reasoning off leaves output unchanged · Self-hosted / llama.cpp+1DeepSeek V4.1 Flash 1017maxOpen+13%-69%$0.26Pass back reasoning_content · Chat Completions+4
Kimi K3maxOpen+13%+256%$2.00Sampling parameters are fixed+3Qwen3.8 FlashthinkingOpen+12%-86%$0.37Context: 400K → 262K+6Kimi K2.6thinkingOpen+12%same$0.71Context: 400K → 256KGPT-6 Astramedium+20%—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium+18%—$0.21Remove unsupported parameters+5GPT-6.1 Terramedium+16%—$0.095GPT-5.6 Solmedium+14%—$0.50GPT-5.5medium+14%—$0.77Prompts with >272K input tokensGPT-6 Solmedium+13%—$0.25GPT-5.3 Codexxhigh+10%—$1.75 / $14DeprecatedGPT-6 Lunamedium+9%—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
7 versionsBenchmarks
in Vision & DocumentsFAQ
How much does GPT-5.4 Mini cost?›
$0.75 per 1M input tokens and $4.50 per 1M output tokens; cached input $0.075 per 1M.
Is GPT-5.4 Mini free to use?›
There is no free API; the cheapest paid price is $0.75 per 1M input tokens.
How good is GPT-5.4 Mini, and what is it best at?›
#131 of 336 in Chat & Knowledge, #51 of 134 in Coding, #53 of 135 in Agents & Tool Use, #86 of 197 in Writing & Language, #68 of 125 in Vision & Documents.
Is GPT-5.4 Mini better than Claude Sonnet 4.6?›
On MMMU-Pro (vision), GPT-5.4 Mini scores 73.3 vs 73.3 — about the same.
How can I use GPT-5.4 Mini?›
Through the API of Azure, OpenAI.
What is the context window of GPT-5.4 Mini?›
400K tokens, with up to 128K output tokens.
When was GPT-5.4 Mini released? Is there a newer version?›
Released 2026-03-17. It has been superseded by GPT-5.6 Terra.
Is GPT-5.4 Mini open source?›
No, GPT-5.4 Mini is a closed model available through an API. The closest open-weights option here is Muse Spark Open.
Can GPT-5.4 Mini read images?›
It accepts text and images, PDF files as input.
What is GPT-5.4 Mini?›
GPT-5.4 Mini is a closed language model from OpenAI, released Mar 2026.
What are the best alternatives to GPT-5.4 Mini?›
Gemini 3.8 Flash (cheaper), GPT-6 Luna (better), Muse Spark Open (open weights).