tokenstat
tokenstat

OpenAI: GPT-6 Astra Pro

openai/gpt-6-astra-pro · rates as of · Benchmarks · AI plans · Calculator

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

Cheapest input
$5
$/MTok · OpenRouter
Cheapest output
$25
$/MTok
Context
1.1M
tokens
Sources
3
8 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
OpenRoutercheapestopenai/gpt-6-astra-pro:batchOpenRouter$5$25$0.51.1M
LiteLLMopenai/gpt-6-astra-pro:batchN/A$5$25$0.5N/A
models.devopenai/gpt-6-astra-proKilo Gateway$10$50$11.1M
models.devopenai/gpt-6-astra-proNanoGPT$10$50$11.1M
OpenRouteropenai/gpt-6-astra-proOpenRouter$10$50$11.1M
LiteLLMopenai/gpt-6-astra-proN/A$10$50$1N/A
LiteLLMgpt-6-astra-proN/A$10$50$1N/A
models.devopenai-gpt-6-astra-proVenice AI$12.50$62.50$1.251.1M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: pdf
  • In: image
  • In: text
  • In: file
  • Out: text
Released: 2026-09-05Family: gpt

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.