🇺🇸 United States🧠 GeneralistReleased August 2025
GPT-5 mini
OpenAI
FreeRGPD
Verdict
Strong value for high-volume usage.
Overview
GPT-5 mini is designed for cases where speed and cost matter more than reasoning depth. Ideal for processing millions of simple queries: classification, moderation, recommendations, etc. Price is 30x lower than GPT-5.
Skill profile
Arena Elo1390
Verified benchmarks
GPQA58%
MATH78.5%
MMLU82.5%
HumanEval85%
What do these scores mean?
GPQA58%solid
PhD-level science questions (physics, chemistry, biology), with no tool access.
MATH78.5%very good
Competition-level math problems.
MMLU82.5%excellent
General knowledge across dozens of academic subjects.
HumanEval85%excellent
Python code generation from specifications.
Strengths
- Strong French quality
- World-class on Arena
- Has a free tier
- Robust safety filters
Who is it for
A good fit if…
- you want to control cost or self-host
- you work in French
- you have GDPR constraints
Skip it if…
Ideal use cases
- High-volume simple tasks
- Classification
- Structured extraction
- Mobile apps
- ChatGPT free tier
Access & availability
Paid API per tokenFree tier available
Key specifications
Context
200K
Input price
$0.15 $/M
Output price
$0.60 $/M
Speed
200 tok/s
Price not auditedBenchmarks not audited
Estimate your monthly cost
Per-token API pricing$8.75/ month with GPT-5 mini
For the same usage
- Gemini 3 Flash$36+314%
- Gemini 3.1 Pro$145+1556%
- GPT-5.5$363+4041%
Indicative estimate based on standard API rates (excluding caching, batch and volume discounts). Always check the official pricing before committing.
Privacy
GDPR-compliantHosting : US/EUAnonymizable data
Advanced data · for expertsArchitecture, modalities, detailed cost, full benchmarks▾
Advanced data · for experts
Architecture, modalities, detailed cost, full benchmarks
Architecture
MoE
Size
undisclosed
Cutoff date
Feb 2025
Inputs
text, image
Outputs
text, code
License
commercial
Hosting
US/EU
Hallucination score
3/5
Estimated cost (API)
Typical exchange (~3k in / 1k out)
≈ $0.0010
1M in + 1M out
≈ $0.75
All benchmarks
| Arena Elo | 1390 |
| MMLU | 82.5% |
| GPQA | 58.0% |
| HumanEval | 85.0% |
| SWE-Bench | — |
| MATH | 78.5% |