Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.

Callable model

GPT-6 Astra API pricing

Use gpt-6-astra through the OpenAI-compatible, Responses, or Anthropic-compatible DiscountedTokens endpoint.

Input / 1M tokens
$0.715
OpenRouter $10.000 · −92%
Output / 1M tokens
$3.575
OpenRouter $50.000 · −92%
Billing
Prepaid
Usage-based · no monthly fee
Price source
Live
Source-backed prices

Compare provider prices

USD per 1M tokens. Input and output compared separately.

Pricing data JSON →
ModelDiscountedTokens
Input / Output
Compare withProvider input / outputInput differenceOutput difference
GPT-6 Astra
gpt-6-astra
$0.715 / $3.575
−92%
OpenRouter ↗
Checked
$10.000 / $50.000
Base token rates only; excludes cache, batch, tools, long context and platform fees.
−92%−92%
GPT-6 Astra
gpt-6-astra
$0.715 / $3.575
−92%
OpenAI ↗
Checked
$10.000 / $50.000
Standard short-context token rates, not Batch, Flex or Fast mode.
−92%−92%
GPT-6 Astra
gpt-6-astra
$0.715 / $3.575
−85%
RunAPI ↗
Checked
$5.000 / $25.000
Starting rates; context-dependent ranges: $5.00-$10.00 / 1M tokens input; $25.00-$37.50 / 1M tokens output.
−85%−85%

Base token rates only; excludes cache, batch, tools, long context and platform fees.

Single discount badges use the smaller input/output saving, rounded down. Quotes older than 24 hours do not generate discount claims. Sources are checked every four hours; availability and model identity are not independently guaranteed.

Successful API requests are billed at the displayed token rates, metered to a fraction of a cent. Charges accumulate and are deducted from your prepaid balance in whole US cents, so a small request is not rounded up to a minimum charge.

OpenAI-compatible quickstart

curl https://discountedtokens.com/v1/chat/completions \ -H "Authorization: Bearer $DISCOUNTEDTOKENS_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"gpt-6-astra","messages":[{"role":"user","content":"Reply OK"}],"max_tokens":8}'

Before production use

Client setup

Browse Codex, Claude Code, Hermes Agent, Python, Node, and cURL tutorials.

Other callable models

Get an API key → All models