openai
GPT-6 Luna (Fast)
GPT-6 Luna is OpenAI's efficient reasoning model for focused, high-volume tasks. It accepts text and images, generates text, and supports a 1,050,000-token context window with up to 128,000 output tokens. Configurable reasoning effort, structured outputs, prompt caching, and Responses API tools support cost-sensitive applications, coding tasks, and automated workflows.
explicit cachingfile inputimplicit cachingreasoningstructured outputtool usevisionweb searchfasttextimagepdf
Overview
- Type
- language
- Context
- 1.1M
- Max output
- 128K
- Input / output
- text, image, pdf / text
API
Model identifier
openai/gpt-6-luna-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 | — | — | — / — / — | $0.10/M | $0.50/M | $0.01/M / $0.13/M | — | us, eu | Yes | Yes |
Pricing
input
0.0000002
input tiers
{
"cost": "0.0000002",
"min": 0,
"max": 272001
}, {
"cost": "0.0000004",
"min": 272001
}
output
0.000001
output tiers
{
"cost": "0.000001",
"min": 0,
"max": 272001
}, {
"cost": "0.0000015",
"min": 272001
}
input cache read
0.00000002
input cache read tiers
{
"cost": "0.00000002",
"min": 0,
"max": 272001
}, {
"cost": "0.00000004",
"min": 272001
}
input cache write
0.00000025
input cache write tiers
{
"cost": "0.00000025",
"min": 0,
"max": 272001
}, {
"cost": "0.0000005",
"min": 272001
}
web search
10
regional
{
"eu": {
"input": "0.0000002",
"input_tiers": [
{
"cost": "0.0000002",
"min": 0,
"max": 272001
},
{
"cost": "0.0000004",
"min": 272001
}
],
"output": "0.000001",
"output_tiers": [
{
"cost": "0.000001",
"min": 0,
"max": 272001
},
{
"cost": "0.0000015",
"min": 272001
}
],
"input_cache_read": "0.00000002",
"input_cache_read_tiers": [
{
"cost": "0.00000002",
"min": 0,
"max": 272001
},
{
"cost": "0.00000004",
"min": 272001
}
],
"input_cache_write": "0.00000025",
"input_cache_write_tiers": [
{
"cost": "0.00000025",
"min": 0,
"max": 272001
},
{
"cost": "0.0000005",
"min": 272001
}
]
},
"us": {
"input": "0.00000022",
"input_tiers": [
{
"cost": "0.00000022",
"min": 0,
"max": 272001
},
{
"cost": "0.00000044",
"min": 272001
}
],
"output": "0.0000011",
"output_tiers": [
{
"cost": "0.0000011",
"min": 0,
"max": 272001
},
{
"cost": "0.00000165",
"min": 272001
}
],
"input_cache_read": "0.000000022",
"input_cache_read_tiers": [
{
"cost": "0.000000022",
"min": 0,
"max": 272001
},
{
"cost": "0.000000044",
"min": 272001
}
],
"input_cache_write": "0.000000275",
"input_cache_write_tiers": [
{
"cost": "0.000000275",
"min": 0,
"max": 272001
},
{
"cost": "0.00000055",
"min": 272001
}
]
}
}
Capabilities
explicit cachingfile inputimplicit cachingreasoningstructured outputtool usevisionweb searchfasttextimagepdf
Supported parameters
max tokens
Yes
temperature
Yes
stop
Yes
tools
Yes
tool choice
Yes
reasoning
Yes
include reasoning
Yes
response format
Yes
structured outputs
Yes
Reasoning options
options
{
"type": "toggle"
}, {
"type": "effort",
"values": [
"none",
"low",
"medium",
"high",
"xhigh",
"max"
]
}
Metadata
type
language
context window
1.1M
max output
128K
knowledge cutoff
2026-05-18
released
Sep 22, 2026
temperature control
Yes
zero data retention
some
no training
all
regions
eu, us
api specifications
v2, v3, v4