Skip to content
llmprice

GPT-5.3 Codex

Updated Sep 11, 2026

gpt-codex400k context128k max outputreleased Feb 5, 2026ReasoningTool calling
Cheapest input
$1.6
Cheapest output
$13
Official (OpenAI)
$14
output per 1M tokens
Providers
29
offering this model
Spread
1.3×
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
PoeCheapest$1.6Cheapest$13$0.16400k
Abacus$1.75$14$0.18400k
AIHubMix$1.75$14$0.175400k
Azure$1.75$14$0.175400k
Azure Cognitive Services$1.75$14$0.175400k
DigitalOcean$1.75$14$0.175400k
Eden AI$1.75$14$0.175400k
FastRouter$1.75$14400k
FreeModel$1.75$14$0.175$1.75400k
FrogBot$1.75$14$0.175400k
Impossibl$1.75$14$0.175400k
Kilo Gateway$1.75$14$0.175400k
DevPass (LLM Gateway)$1.75$14$0.175400k
LLM Gateway$1.75$14$0.175400k
LLM Gateway$1.75$14$0.175400k
NanoGPT$1.75$14$0.175400k
Neon$1.75$14$0.175400k
Ofox$1.75$14$0.18400k
OpenAI$1.75$14$0.175400k
OpenCode Zen$1.75$14$0.175400k
OpenRouter$1.75$14$0.175400k
Opper$1.75$14$0.175400k
OrcaRouter$1.75$14$0.175400k
Pioneer$1.75$14$0.175$1.75400k
Requesty$1.75$14$0.175400k
Vercel AI Gateway$1.75$14$0.175400k
Vivgrid$1.75$14$0.175400k
ZenMux$1.75$14400k
Venice AI$2.19$17.5$0.219400k

Subscription plans (not per-token)

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

Provider1M input1M outputContext
GitHub Copilotplan$1.75$14400k

Other gpt-codex models