Loading model details
Hosted by a provider reached through SayGM. The route is sealed in transit and in use; the provider receives the prompt under its API terms.
Released
Sep 2026Knowledge cutoff
Apr 2026Modalities
Text · Tool calling · Image inputBest reported price on SayGM
-22.5%In
Cached
Out
per Mtok*
Create an API key and set it as SAYGM_API_KEY in your terminal.
curl "https://api.saygm.com/v1/chat/completions" \
-H "Authorization: Bearer $SAYGM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-astra",
"messages": [
{
"role": "user",
"content": "Hello!"
}
]
}'SayGM's best reported rate for gpt-6-astra next to OpenAI's own published list price — 22.5% off.
| Dimension | SayGM price | OpenAI list price |
|---|---|---|
| Input | $7.75per Mtok | $10.00 |
| Output | $38.75per Mtok | $50.00 |
| Cache read | $0.775per Mtok | $1.00 |
| Cache write | $9.6875 |
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$8.99
$10.00Cached input
$0.90
$1.00Output
$42.09
$50.00Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 1 window: 95 requests and 3,731,419 input-side tokens. Most recent window closed 2026-10-07 00:37 UTC.
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 22.5% off |
Explore the OpenAI lab and compare related models.
The best reported rate for gpt-6-astra on SayGM is $7.75 per million input tokens and $38.75 per million output tokens. A request above 272,000 input tokens bills at SayGM's long-context rate instead.
SayGM's best reported rate for gpt-6-astra is 22.5% off OpenAI's list price.
Yes. gpt-6-astra is served on SayGM's OpenAI-compatible chat/completions surface, so an unmodified OpenAI SDK pointed at SayGM's base URL works with it.
| $12.50 |
| Long-context inputabove 272,000 input tokens | $15.50per Mtok | $20.00 |
| Long-context outputabove 272,000 input tokens | $58.125per Mtok | $75.00 |
| Long-context cache readabove 272,000 input tokens | $1.55per Mtok | $2.00 |
| Long-context cache writeabove 272,000 input tokens | $19.375per Mtok | $25.00 |
| $7.75 |
| $38.75 |
| Provider 2 | 22.0% off | $7.80 | $39.00 |
| Provider 3 | 20.0% off | $8.00 | $40.00 |
| Provider 4 | 20.0% off | $8.00 | $40.00 |
| Provider 5 | 10.0% off | $9.00 | $45.00 |
| Provider 6 | 10.0% off | $9.00 | $45.00 |
| Provider 7 | 10.0% off | $9.00 | $45.00 |
| Provider 8 | 10.0% off | $9.00 | $45.00 |
| Provider 9 | 10.0% off | $9.00 | $45.00 |
| Provider 10 | 10.0% off | $9.00 | $45.00 |
| Provider 11 | 10.0% off | $9.00 | $45.00 |
| Provider 12 | 10.0% off | $9.00 | $45.00 |
| Provider 13 | 10.0% off | $9.00 | $45.00 |
| Provider 14 | 10.0% off | $9.00 | $45.00 |
| Provider 15 | 10.0% off | $9.00 | $45.00 |
Measured on the requests SayGM routed to this model.
Fixed-seed suites SayGM runs against this model.