GPT-5.4 Mini (2026-03-17)
Mar 2026
GPT-5.4 Mini (2026-03-17)Compare inon
GPT-5.4 Mini (2026-03-17) measured on 9 of 109 Chat & Knowledge benchmarks9
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math4
Legacy · saturated or no longer reported2
No benchmark matches
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperDeepSeek V4.1 Flash 1017maxOpen×4.5-69%$0.26Pass back reasoning_content · Chat Completions+4BetterGPT-5.6 Lunalow+55%-73%$0.01
CheaperGemini 3.8 Flashhigh×4.3-11%*$3.49Sampling parameters are ignored+1
CheaperClaude Haiku 5.5max×2.7-88%$0.21Remove sampling parameters+5CheaperGemini 3.6 Flashhigh×2.7-11%*$1.60ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×4.5-69%$0.26Pass back reasoning_content · Chat Completions+4Gemini 3.8 Flashhigh×4.3-11%*$3.49Sampling parameters are ignored+1Claude Haiku 5.5max×2.7-88%$0.21Remove sampling parameters+5Gemini 3.6 Flashhigh×2.7-11%*$1.60Gemini 3 Flash Previewlow×2.4-33%$0.50 / $3ModelScoreCostPer taskWhat changes
GPT-5.6 Lunalow+55%-73%$0.01GPT-5.6 Terralow+73%+167%$0.14Prompts with >272K input tokensClaude Haiku 5.5max×2.7-88%$0.21Remove sampling parameters+5GPT-5.6 Sollow×2.4+374%$0.26DeepSeek V4.1 Flash 1017maxOpen×4.5-69%$0.26Pass back reasoning_content · Chat Completions+4ModelScoreCostPer taskWhat changes
DeepSeek V4.1 Flash 1017maxOpen×4.5-69%$0.26Pass back reasoning_content · Chat Completions+4DeepSeek V4 Pro 0813maxOpen×3.9+17%$0.67No image input+5
GLM 5.3maxOpen×3+27%$2.01No image input+4
Kimi K3maxOpen×2.4+256%$2.00Sampling parameters are fixed+3
Qwen3.6 35B A3BnoneOpen×2-67%$0.25 / $1.49Context: 400K → 262KModelScoreCostPer taskWhat changes
GPT-6 Astramax×7.6—$3.26Monitoring can return HTTP 403+2GPT-6.1 Solmax×7.3—$0.72Remove unsupported parameters+5GPT-6 Solmax×5.1—$1.04GPT-5.6 Solnone×3—$4 / $20o3 (2025-04-16)medium×2.1—$2 / $8Context: 400K → 200KGPT-5.6 Lunanone+82%—$0.20 / $1.20GPT-5.5none+64%—$5 / $30Prompts with >272K input tokensGPT-5.4 (2026-03-05)none+45%—$2.50 / $15All OpenAI models →History
7 versionsBenchmarks
in Chat & KnowledgeGPQA Diamond · Epoch64.1#89
OTIS Mock AIME 2024 202526.7#102
FrontierMath Tiers 1–3 (v2)17.2#66
Chess Puzzles2#68
Mystery Game Puzzles11#54
FAQ
How much does GPT-5.4 Mini (2026-03-17) cost?›
$0.75 per 1M input tokens and $4.50 per 1M output tokens.
Is GPT-5.4 Mini (2026-03-17) 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 (2026-03-17), and what is it best at?›
#59 of 84 in Chat & Knowledge.
Is GPT-5.4 Mini (2026-03-17) better than Qwen3.6 Plus?›
On Mystery Game Puzzles, GPT-5.4 Mini (2026-03-17) scores 11 vs 12 — lower.
How can I use GPT-5.4 Mini (2026-03-17)?›
Through the OpenAI API.
What is the context window of GPT-5.4 Mini (2026-03-17)?›
400K tokens.
When was GPT-5.4 Mini (2026-03-17) released? Is there a newer version?›
Released 2026-03-17. It is the current version in its line.
Can GPT-5.4 Mini (2026-03-17) read images?›
It accepts text and images as input.
What is GPT-5.4 Mini (2026-03-17)?›
GPT-5.4 Mini (2026-03-17) is a language model from OpenAI, released Mar 2026.
What are the best alternatives to GPT-5.4 Mini (2026-03-17)?›
DeepSeek V4.1 Flash 1017 (cheaper), GPT-5.6 Luna (better).