gpt-5-mini
Near-frontier intelligence for cost sensitive, low latency, high volume workloads
Capabilities
- Reasoning
- Tool calling
- Structured output
- Image input
- File input
Use gpt-5-mini in your agent
Set the model name in your agent configuration. Each run costs 3 credits / run.
LLM_config:
params:
model: gpt-5-miniOpen SVAHNARSpecifications
Provider
OpenAI
Model name (config ID)
gpt-5-mini
Credits
3 credits / run
Context window
400K tokens
Max output
128K tokens
Input
text, image
Output
text
Knowledge cutoff
May 2024
Released
August 2025
Subscription
Required