openai
GPT-6 Astra (Fast)
GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.
file inputimplicit cachingreasoningtool usevisionweb searchwebsocket realtimeexplicit cachingstructured outputfasttextimagepdf
Overview
- Type
- language
- Context
- 1.1M
- Max output
- 128K
- Input / output
- text, image, pdf / text
API
Model identifier
openai/gpt-6-astra-fastProviders and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| openai | Operational | — | — | — / — / — | $10.00/M | $50.00/M | $1.00/M / $12.50/M | — | us, eu | Yes | Yes |
Pricing
input
0.00002
input tiers
{
"cost": "0.00002",
"min": 0,
"max": 272001
}, {
"cost": "0.00004",
"min": 272001
}
output
0.0001
output tiers
{
"cost": "0.0001",
"min": 0,
"max": 272001
}, {
"cost": "0.00015",
"min": 272001
}
input cache read
0.000002
input cache read tiers
{
"cost": "0.000002",
"min": 0,
"max": 272001
}, {
"cost": "0.000004",
"min": 272001
}
input cache write
0.000025
input cache write tiers
{
"cost": "0.000025",
"max": 272001
}, {
"cost": "0.00005",
"min": 272001
}
web search
10
regional
{
"eu": {
"input": "0.00002",
"input_tiers": [
{
"cost": "0.00002",
"min": 0,
"max": 272001
},
{
"cost": "0.00004",
"min": 272001
}
],
"output": "0.0001",
"output_tiers": [
{
"cost": "0.0001",
"min": 0,
"max": 272001
},
{
"cost": "0.00015",
"min": 272001
}
],
"input_cache_read": "0.000002",
"input_cache_read_tiers": [
{
"cost": "0.000002",
"min": 0,
"max": 272001
},
{
"cost": "0.000004",
"min": 272001
}
],
"input_cache_write": "0.000025",
"input_cache_write_tiers": [
{
"cost": "0.000025",
"max": 272001
},
{
"cost": "0.00005",
"min": 272001
}
]
},
"us": {
"input": "0.000022",
"input_tiers": [
{
"cost": "0.000022",
"min": 0,
"max": 272001
},
{
"cost": "0.000044",
"min": 272001
}
],
"output": "0.00011",
"output_tiers": [
{
"cost": "0.00011",
"min": 0,
"max": 272001
},
{
"cost": "0.000165",
"min": 272001
}
],
"input_cache_read": "0.0000022",
"input_cache_read_tiers": [
{
"cost": "0.0000022",
"min": 0,
"max": 272001
},
{
"cost": "0.0000044",
"min": 272001
}
],
"input_cache_write": "0.0000275",
"input_cache_write_tiers": [
{
"cost": "0.0000275",
"max": 272001
},
{
"cost": "0.000055",
"min": 272001
}
]
}
}
Capabilities
file inputimplicit cachingreasoningtool usevisionweb searchwebsocket realtimeexplicit cachingstructured outputfasttextimagepdf
Supported parameters
max tokens
Yes
stop
Yes
tools
Yes
tool choice
Yes
reasoning
Yes
include reasoning
Yes
response format
Yes
structured outputs
Yes
Reasoning options
options
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
Metadata
type
language
context window
1.1M
max output
128K
knowledge cutoff
2026-04-30
released
Sep 4, 2026
temperature control
No
zero data retention
some
no training
all
regions
eu, us
api specifications
v2, v3, v4