OpenAI: GPT-5 Mini
openai/gpt-5-mini
GPT-5 Mini (OpenAI) ranks #79 of 235 on the TryAii Score at $0.25/$2 per million input/output tokens — a little under the going rate for its score class, though DeepSeek V4 Flash 0423 matches it for $0.177 per million output tokens. It's strongest on instruction-following (#4 on IFEval). It's among the fastest models we track, at roughly 58-68 tokens/sec.
Prompt $/1M
$0.250
Completion $/1M
$2.000
Context
400,000 tok
Best provider
74 tok/s · OpenAI
Specs
- Model id
- openai/gpt-5-mini
- Display name
- OpenAI: GPT-5 Mini
- Modality
- text+image+file->text
- Tokenizer
- GPT
- Instruct type
- —
- Context length
- 400,000
- Max completion
- 128,000
- Prompt $/1M
- $0.250
- Completion $/1M
- $2.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedyes
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| OpenAIfastest | 74 |
| Azure | 52 |
| openaifastest | — |
| Artificial Analysis | 0 |
Prompt caching by provider
| Provider | Min tokens to cache |
|---|---|
| OpenAI | 1,024 tokens |