Loading...

TopxAI · Model prices · OpenAI

GPT-6.2 Astra API pricing

Model id gpt-6.2-astra. $6.4 input / $32 output per 1M tokens, next to the provider's list price below. Prices are fixed in USD, charged from prepaid credit, and every request writes one usage-log row with the route and the charge.

GPT-6.2 Astra supports reasoning and coding with a 1.05M-token context and 128K maximum output. Prompts with more than 272K input tokens are billed at the long-context rate (2x input and cache, 1.5x output) for the full request.

Prices by route

RouteInput (USD / 1M tokens)Output (USD / 1M tokens)Cache read (USD / 1M tokens)Cache write (USD / 1M tokens)Cache write (1h) (USD / 1M tokens)
Provider list price (checked 2026-11-18)
Cache write references use the default 30-minute TTL.
$8$40$0.4$10—
Provider list price (checked 2026-11-18)
Cache write references use the default 30-minute TTL., from 272,001 input tokens (whole request)
$16$60$0.8$20—
TopxAI price$6.4$32$0.32$8—
TopxAI price, from 272,001 input tokens (whole request)$12.8$48$0.64$16—

Web search: $10 per 1,000 searches, the provider's official price, charged only when the model searches. The pages it reads are billed as input tokens.

Input, output and cache lanes bill per million tokens. A whole-request long-context row applies once the input context of a request reaches the threshold shown. An Auto-route key bills every model on its own route.

Endpoints

Call gpt-6.2-astra

Base URL https://api.topxai.xyz/v1 for OpenAI-style SDKs, https://api.topxai.xyz for the Anthropic SDK; the API key goes where the provider's key would go.

curl https://api.topxai.xyz/v1/chat/completions \
  -H "Authorization: Bearer $TOPXAI_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model": "gpt-6.2-astra", "messages": [{"role": "user", "content": "Say hello in one sentence."}]}'

Related

Get an API key · Docs · Blog · About TopxAI