Skip to content
llmprice

GPT-6 Astra

Updated Sep 11, 2026

gpt-astra1.1M context1.1M max outputreleased Sep 4, 2026ReasoningTool calling
Cheapest input
$10
Cheapest output
$50
Official (OpenAI)
$50
output per 1M tokens
Providers
21
offering this model
Spread
1.1×
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
302.AICheapest$10Cheapest$501.1M
Amazon Bedrockglobal$10$50$1$12.51.1M
Azure$10$50$1$12.51.1M
CrossModel$10$50$1$12.51.1M
DigitalOcean$10$50$11.1M
Eden AI$10$50$1$12.51.1M
Kilo Gateway$10$50$1$12.51.1M
DevPass (LLM Gateway)$10$50$1$12.51.1M
LLM Gateway$10$50$1$12.51.1M
LLM Gateway$10$50$1$12.51.1M
Merge Gateway$10$50$11.1M
NanoGPT$10$50$1$12.51.1M
Neon$10$50$1$12.51.1M
Ofox$10$50$1$12.51.1M
OpenAI$10$50$1$12.51.1M
OpenCode Zen$10$50$1$12.51.1M
OpenRouter$10$50$1$12.51.1M
Requesty$10$50$11.1M
Venice AI$10$50$1$12.51.1M
Vercel AI Gateway$10$50$1$12.51.1M
Vivgrid$10$50$1$12.51.1M
Amazon Bedrock$11$55$1.1$13.751.1M
Amazon Bedrockus$11$55$1.1$13.751.1M

Subscription plans (not per-token)

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

Provider1M input1M outputContext
GitHub Copilotplan$10$501.1M

Other gpt-astra models