HyperFlowAll models
Released: Sep 15, 2026
OpenAI
GPT-6 Astra
Modalities
openai/gpt-6-astraOpenAI's most capable model with 1.05M context window and 128K max output. Supports 5 reasoning effort levels, vision, computer use, function calling, structured outputs, and prompt caching.
Context
1.05M tokens
Input / 1M
from $4.40
Output / 1M
from $22.00
Cache read / 1M
from $1.00
Cache write / 1M
from $12.50
Best offer: $50.00 → $22.00 per 1M output tokens-56%
Pricing
USD · per 1M tokens
0 – 272K
Input
$4.40
Output
$22.00
Cache read
$1.00
Cache write
$12.50
272K – 1.05M
Input
$20.00
Output
$75.00
Cache read
$2.00
Cache write
$25.00
Context range | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| 0 – 272K | $4.40 | $22.00 | $1.00 | $12.50 |
| 272K – 1.05M | $20.00 | $75.00 | $2.00 | $25.00 |
Offers
1 seller
Surplus Intelligence
Price
Infrom $4.40Outfrom $22.00
Discount
-56%
Latency
—
Seller | Price | Discount | Latency |
|---|---|---|---|
| Surplus Intelligence | Infrom $4.40Outfrom $22.00 | -56% | — |
Usage · 30D
No usage yet
Get started
curl https://super.hyperflow.fun/v1/chat/completions \
-H "Authorization: Bearer $HYPERFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6-astra",
"messages": [{ "role": "user", "content": "Hello!" }]
}'
