API pricing per million tokens
gpt-5-mini ReasoningChecked 5h ago
- Input
- $0.25
- per 1M, list
- Output
- $2
- per 1M tokens
- Cached input
- $0.025
- batch $0.125 / $1
- Context
- 400K
- 128K max output
Where to buy it (4)
OpenAIflex-50%$0.125 / $1cached $0.013
Azure AI Foundrydefault region$0.25 / $2cached $0.03
Through a gateway
Your own numbers100M input and 20M output tokens a month: $65.00 direct.
Helicone$65.00+0%
Kong AI Gateway$65.00+0%
LiteLLM$65.00+0%
Vercel AI Gateway$65.00+0%
AWS Bedrock$65.00+0%
Google Vertex AI$65.00+0%
Databricks Mosaic AI$65.00+0%
Hugging Face Inference$65.00+0%
Cloudflare AI Gateway$68.25+5%
Requesty$68.25+5%
Eden AI$68.58+5.5%
OpenRouter$68.58+5.5%
Snowflake Cortex AI$78.00+20%
Martian Gatewayn/a
Portkeyn/a
TrueFoundry AI Gatewayn/a
IBM watsonx.ain/a
OCI Generative AIn/a
NVIDIA NIMn/a
Related models
ModelInputOutputCachedContextReleased
Gemini 3.8 FlashGoogle Gemini API · 1M$0.75 / $3.75in / out per 1M$0.75$3.75$0.0751MSep 2, 2026
GLM 5.3Z.ai · via DeepInfra (fp4) · 1.31M$0.563 / $2.5in / out per 1M$0.563$2.5$0.1251.31MAug 18, 2026
About GPT-5 Mini
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks.
Takes text, image, files in and returns text. First listed Aug 12, 2025. Blended price $0.688 per 1M tokens at 3 input to 1 output.
Questions
How much does GPT-5 Mini cost?
$0.25 per million input tokens and $2 per million output tokens, with cached input at $0.025, or $0.125 and $1 through the Batch API.
What is the context window of GPT-5 Mini?
400K tokens, with up to 128K tokens of output.
Where is GPT-5 Mini cheapest?
Of 4 routes tracked, OpenAI is cheapest at $0.125 input and $1 output per million tokens.
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.