GPT-5 (2025-08-07) vs GPT-5 mini

GPT-5 (2025-08-07) vs GPT-5 mini: GPT-5 mini is cheaper by 80% on average. GPT-5 (2025-08-07) from Azure OpenAI (272,000-token context, reasoning, tool calls) vs. GPT-5 mini from OpenAI (272,000-token context, reasoning, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.

Side-by-side cost

Live workload comparison

Same workload run through both models. The cheaper one is highlighted.

3,000
0272,000
400
0128,000
5,000
01,000,000
Azure OpenAI
$1,179/mo
Input $1.25/M · Output $10.00/M
GPT-5 miniCheaper
OpenAI
$236/mo
Input $0.250/M · Output $2.00/M
At this workload, GPT-5 mini is 80% cheaper than GPT-5 (2025-08-07) — a savings of $944/month ($11,323/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: gpt-5-mini
  provider: openai
fallback:
  model: gpt-5-2025-08-07
  provider: azure-openai
shadow: { sample_rate: 0.05 }   # mirror 5% of traffic to compare quality live
GPT-5 (2025-08-07) GPT-5 mini
Input price $1.25/M $0.250/M
Output price $10.00/M $2.00/M
Context window 272,000 272,000
Max output 128,000 128,000
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~80% cheaper than GPT-5 (2025-08-07)
Larger context
272,000 tokens
More capabilities
5 of 6 capability flags advertised

Benchmark comparison

Side-by-side public benchmark scores. Greener bar = winner.

Chatbot Arena ELOgeneral
GPT-5 (2025-08-07)
1,450
GPT-5 mini
1,395
MATH-500math
GPT-5 (2025-08-07)
99.6%
GPT-5 mini
AIME 2024math
GPT-5 (2025-08-07)
98.4%
GPT-5 mini
91.1%
BFCL v3agent
GPT-5 (2025-08-07)
96.3%
GPT-5 mini
HumanEvalcode
GPT-5 (2025-08-07)
96.0%
GPT-5 mini
93.5%
IFEvalgeneral
GPT-5 (2025-08-07)
95.6%
GPT-5 mini
AIME 2025math
GPT-5 (2025-08-07)
94.6%
GPT-5 mini
LiveCodeBenchcode
GPT-5 (2025-08-07)
90.0%
GPT-5 mini
MMLU-Proreasoning
GPT-5 (2025-08-07)
89.4%
GPT-5 mini
82.0%
Aider Polyglotcode
GPT-5 (2025-08-07)
88.0%
GPT-5 mini
GPQA Diamondreasoning
GPT-5 (2025-08-07)
87.3%
GPT-5 mini
78.4%
MMMUmultimodal
GPT-5 (2025-08-07)
84.2%
GPT-5 mini
SWE-bench Verifiedagent
GPT-5 (2025-08-07)
74.9%
GPT-5 mini
68.0%
Humanity's Last Examreasoning
GPT-5 (2025-08-07)
42.0%
GPT-5 mini
ARC-AGI-2reasoning
GPT-5 (2025-08-07)
17.6%
GPT-5 mini