Celon

GPT-5 mini

ChatInput: TextInput: ImageInput: FileReleased Aug 7, 2025

Built by OpenAI · United States · openai.com

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....

How to use

model: "openai/gpt-5-mini"

Cap quality here and save

Hard questions go to this model, easy ones drop to something cheaper. Set a savings target (0–0.8) and the router tunes itself until realized savings converge on it.

{
  "model": "celon/auto",
  "celon": {
    "anchor": "openai/gpt-5-mini",
    "savings_target": 0.4
  }
}

Naming a model directly gets you that model — savings controls don't apply.

Context

400K

Max output

128K

Input $/1M

$0.25

Output $/1M

$2.00

Features

Image inputTool callingJSON

Serving providers

OpenAI

Providers

Price, latency, and uptime per provider serving this model. Celon routes each request to the fastest and cheapest of them. Click a row for regions and data policies.

Loading provider metrics…

Performance

Benchmark quality scores, and measured speed per provider.

Quality

Epoch Capabilities IndexComposite over 50+ benchmarks
145.8
GPQA DiamondPhD-level science questions
75.0%
AIMECompetition mathematics
86.7%
FrontierMathResearch-level mathematics
27.2%
SWE-bench VerifiedReal GitHub issue resolution
64.7%
Terminal-BenchAgentic terminal tasks
34.8%
SciCodeScientific code generation
39.2%
ARC-AGI-2Abstract reasoning
4.4%
SimpleQA VerifiedFactual accuracy
21.0%
HLEHumanity's Last Exam
19.4%

At each model's best reasoning effort. Benchmarks it wasn't run on are omitted.

Speed

Loading provider metrics…