Skip to content
llmprice

GPT-5 Mini

Updated Sep 11, 2026

gpt-mini400k context128k max outputreleased Aug 7, 2025ReasoningTool calling
Cheapest input
$0.04
Cheapest output
$0.29
Official (OpenAI)
$2
output per 1M tokens
Providers
35
offering this model
Spread
7.6×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
QiHangCheapest$0.04Cheapest$0.29200k
Poe$0.22$1.8$0.022400k
Jiekou.AI$0.225$1.8400k
302.AI$0.25$2400k
Abacus$0.25$2$0.025400k
Azure$0.25$2$0.03400k
Azure Cognitive Services$0.25$2$0.03400k
Cloudflare AI Gateway$0.25$2$0.025128k
Databricks$0.25$2$0.025400k
DigitalOcean$0.25$2$0.025400k
Eden AI$0.25$2$0.025400k
FastRouter$0.25$2$0.025400k
Helicone$0.25$2$0.025400k
Impossibl$0.25$2$0.025400k
Kilo Gateway$0.25$2$0.025400k
DevPass (LLM Gateway)$0.25$2$0.025400k
LLM Gateway$0.25$2$0.025400k
LLM Gateway$0.25$2$0.025400k
Merge Gateway$0.25$2$0.025400k
NanoGPT$0.25$2$0.025400k
NEAR AI Cloud$0.25$2$0.025400k
Neon$0.25$2$0.025400k
Ofox$0.25$2$0.03256k
OpenAI$0.25$2$0.025400k
OpenRouter$0.25$2$0.025400k
OrcaRouter$0.25$2$0.025400k
Perplexity Agent$0.25$2$0.025400k
Pioneer$0.25$2$0.025$0.25400k
SAP AI Core$0.25$2$0.025400k
Vercel AI Gateway$0.25$2$0.025400k
Vivgrid$0.25$2$0.03272k
Requestyeu$0.275$2.2$0.0275200k
Cortecs$0.279$2.192$0.056400k

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

Provider1M input1M outputContext
GitHub Copilotplan$0.25$2264k

Other gpt-mini models