Skip to content

Providers / OpenAI · All access methods for openai/gpt-6-astra

GPT-6 Astra

openai/gpt-6-astra API key models.dev2026-11-17providers.dev2026-11-11

Type chat · Released 2026-09-04

Input window
922,000 tokensdocumented
models.dev · 2026-11-17
Input alone
Context window
1,050,000 tokens
Exposed by this provider
Maximum output
128,000 tokens
Per response; not a default
Cache lifetime, short
30 mindocumented
models.dev · 2026-11-17
Measured 30 min
Cache lifetime, long
12 hdocumented
models.dev · 2026-11-17

Limits

Input window

LimitValueSource
Input window
input_window: the most input one request can carry on this entry, in tokens as the provider counts them.
922,000 tokensdocumentedInput alonemodels.dev2026-11-17
Documented
The figure the source documents, and the field it is in.
922,000 tokenslimit.inputmodels.dev2026-11-17
Measured
What each limit evaluation that counts gives, one line per evaluation.
Not measured–

How the input window is worked out, and what it does not say

Documented

LimitValueSource
Context window
limit.context: what this provider accepts for the model, input and output together.
1,050,000 tokensmodels.dev
Largest input
limit.input: stated where the input limit is lower than the context window.
922,000 tokensmodels.dev
Maximum output
limit.output: the most one response can hold. A maximum, not what you get by default.
128,000 tokensmodels.dev

Measured tokens

DateMeasured throughContextInput acceptedInput refusedOutput limitRequested output acceptedEvidence
No limits were measured on this entry.

Price

Base chargeRate
Input$10 / 1M tokens
Output$50 / 1M tokens
Reasoning outputUnknown
Cache read$1 / 1M tokens
Cache write$12.50 / 1M tokens · 30 min lifetime
$25 / 1M tokens · 12 h lifetime
Web search$10 / 1,000 searches

Conditional rates

ConditionChargeRateApplies to
Context above 272,000 tokensInput$20 / 1M tokensWhole request
Output$75 / 1M tokens
Cache read$2 / 1M tokens
Context above 272,000 tokens and cache lifetime 30 minCache write$25 / 1M tokensWhole request
Context above 272,000 tokens and cache lifetime 12 hCache write$50 / 1M tokensWhole request
Service tier priorityInput$20 / 1M tokens · × 2Whole request
Output$100 / 1M tokens · × 2
Cache read$2 / 1M tokens · × 2
Service tier ultrafastInput$60 / 1M tokens · × 6Whole request
Output$300 / 1M tokens · × 6
Cache read$6 / 1M tokens · × 6
Service tier flexInput$5 / 1M tokens · × 0.5Whole request
Output$25 / 1M tokens · × 0.5
Cache read$0.50 / 1M tokens · × 0.5
Any region but globalInput$11 / 1M tokens · × 1.1Whole request
Output$55 / 1M tokens · × 1.1
Cache read$1.10 / 1M tokens · × 1.1

Source: models.dev 2026-11-17

Other prices in the source, not shown above (0)

None

Request controls

ControlSupportRequest fieldAccepted valuesDefaultConditions
Service tierSupportedUnknown
flex
priority
ultrafast
UnknownNone recorded

Source: models.dev 2026-11-17

Prompt caching

Lifetimes

Every cache lifetime of this entry, by retention
LifetimeDocumented for, or measured throughTime since the prompt was cached · served from the cache, in percent, with hits/checks
At once2.5 min5 min7.5 min10 min15 min20 min25 min30 min40 min50 min1 h1 h 151 h 302 h4 h8 h12 h24 h
Short retention
Safe lifetime
30 mindocumentedmodels.dev2026-11-17Documentation not contradicted
Documented
30 min
Measured
30 min · 1 client
Inside the documented lifetime
10 of 10 checks hit
30 mindocumentedmodels.dev2026-11-17Manual explicit
As documented: 30m
Not applicable
30 minmeasuredproviders.dev2026-11-11Requests sent through CLIProxyAPI
No lifetime asked for · 10 of 16 checks hit
Tested from 5 min · First miss 40 min
1 evaluation
1001/1·1003/3··1003/3··1003/300/3·00/3·······
gpt6-2026-11-11/G6 2026-11-11
OpenAI API key
Raw result
1001/1·1003/3··1003/3··1003/300/3·00/3·······
Long retention
Safe lifetime
12 hdocumentedmodels.dev2026-11-17
Documented
12 h
Measured
Not measured
Inside the documented lifetime
Not applicable
12 hdocumentedmodels.dev2026-11-17Manual explicit
As documented: 12h
Not applicable

Checks served from the cache, in percent and as hits/checks, by time since the prompt was cached100 All67 Half or more33 Fewer0 None· Not checked at that ageMethodology

Cache modes

ModeSupportedMin. tokensBreakpointsTargets
Automatic implicit Supported 1,024 Not applicable Not applicable
Manual explicit Supported 1,024 4 Unknown

Source: models.dev · Cache modes

Retention

ControlSupportRequest fieldAccepted valuesDefaultConditions
Cache retentionSupportedprompt_cache_options.ttl
Request body, top level
prompt_cache_breakpoint.ttl
Request body, on a content block
Short: 30m
Long: 12h
30m"12h" is documented for the Responses API only.

Source: developers.openai.com/api/docs/guides/prompt-caching#cache-lifetime-gpt-5-6-and-later 2026-11-14

Provenance

ProvenanceValue
Sourcemodels.dev2026-11-17providers.dev2026-11-11
Inherited fromNone
CorrectionsNone
EvidenceNone

Data

GET /api/v1/entries/openai/gpt-6-astra

Show the full entry as published
{
  "id": "gpt-6-astra",
  "name": "GPT-6 Astra",
  "description": "GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.",
  "type": "chat",
  "family": "gpt-astra",
  "canonical_id": "openai/gpt-6-astra",
  "release_date": "2026-09-04",
  "limit": {
    "context": 1050000,
    "input": 922000,
    "output": 128000
  },
  "capabilities": {
    "cache": {
      "implicit": {
        "min_tokens": 1024
      },
      "explicit": {
        "ttl": [
          "30m",
          "12h"
        ],
        "min_tokens": 1024,
        "max_breakpoints": 4
      }
    },
    "temperature": false,
    "top_k": false,
    "top_p": false,
    "structured_output": true,
    "prompt_cache_key": true,
    "store": true,
    "system_updates": true,
    "effort_updates": false,
    "service_tier": [
      "flex",
      "priority",
      "ultrafast"
    ],
    "tools": {
      "supported": true
    },
    "reasoning": {
      "supported": true,
      "effort": [
        "low",
        "medium",
        "high",
        "xhigh",
        "max"
      ]
    }
  },
  "cost": {
    "text": {
      "input": {
        "price": 10,
        "cache": {
          "read": 1,
          "write": {
            "30m": 12.5,
            "12h": 25
          }
        },
        "overrides": [
          {
            "when": {
              "context": {
                "gt": 272000
              }
            },
            "price": 20,
            "cache": {
              "read": 2,
              "write": {
                "30m": 25,
                "12h": 50
              }
            }
          }
        ]
      },
      "output": {
        "price": 50,
        "overrides": [
          {
            "when": {
              "context": {
                "gt": 272000
              }
            },
            "price": 75
          }
        ]
      }
    },
    "multipliers": [
      {
        "when": {
          "service_tier": {
            "equals": "priority"
          }
        },
        "factor": {
          "text": 2
        }
      },
      {
        "when": {
          "service_tier": {
            "equals": "ultrafast"
          }
        },
        "factor": {
          "text": 6
        }
      },
      {
        "when": {
          "service_tier": {
            "equals": "flex"
          }
        },
        "factor": {
          "text": 0.5
        }
      },
      {
        "when": {
          "not": {
            "region": {
              "equals": "global"
            }
          }
        },
        "factor": {
          "text": 1.1
        }
      }
    ],
    "web_search": {
      "price": 10
    }
  },
  "modalities": {
    "input": [
      "text",
      "image/jpeg",
      "image/png",
      "image/gif",
      "image/webp",
      "application/pdf"
    ],
    "output": [
      "text"
    ]
  },
  "api": {
    "responses": {
      "base_url": "https://api.openai.com/v1",
      "sdk": {
        "aisdk": "@ai-sdk/openai",
        "opencodeai": "@opencode/ai/providers/openai/responses"
      },
      "capabilities": {
        "effort_updates": true,
        "tools": {
          "choice": [
            "auto",
            "none",
            "required",
            "tool"
          ],
          "freeform": [
            "text",
            "lark",
            "regex"
          ],
          "strict": true,
          "updates": true,
          "search": true
        }
      }
    },
    "chat-completions": {
      "base_url": "https://api.openai.com/v1",
      "sdk": {
        "aisdk": "@ai-sdk/openai",
        "opencodeai": "@opencode/ai/providers/openai/chat"
      },
      "capabilities": {
        "tools": {
          "choice": [
            "auto",
            "none",
            "required",
            "tool"
          ],
          "freeform": [
            "text",
            "lark",
            "regex"
          ],
          "updates": false
        }
      }
    }
  },
  "open_weights": false,
  "knowledge": "2026-04-30",
  "last_updated": "2026-09-04",
  "experimental": {
    "modes": {
      "fast": {
        "service_tier": "priority",
        "body": {
          "service_tier": "priority"
        }
      },
      "flex": {
        "body": {
          "service_tier": "flex"
        }
      },
      "pro": {
        "body": {
          "reasoning": {
            "mode": "pro"
          }
        }
      },
      "ultrafast": {
        "body": {
          "service_tier": "ultrafast"
        }
      }
    }
  },
  "providers_dev": {
    "origin": "upstream",
    "access": "api",
    "provenance": [],
    "inherited": null,
    "cache": {
      "documented": {
        "support": "supported",
        "modes": {
          "implicit": {
            "support": "supported",
            "min_tokens": 1024,
            "max_breakpoints": null,
            "targets": null
          },
          "explicit": {
            "support": "supported",
            "min_tokens": 1024,
            "max_breakpoints": 4,
            "targets": null
          }
        }
      },
      "retention": {
        "support": "supported",
        "parameter": {
          "name": "prompt_cache_options.ttl",
          "location": "Request body, top level"
        },
        "accepted_values": [
          "30m",
          "12h"
        ],
        "default": "30m",
        "profiles": [
          {
            "profile": "short",
            "value": "30m"
          },
          {
            "profile": "long",
            "value": "12h"
          }
        ],
        "conditions": [
          "\"12h\" is documented for the Responses API only."
        ],
        "evidence": [
          {
            "kind": "documented",
            "url": "https://developers.openai.com/api/docs/guides/prompt-caching#cache-lifetime-gpt-5-6-and-later",
            "date": "2026-11-14",
            "note": "GPT-5.6 and later: 'In the Responses API, set prompt_cache_options.ttl to choose the minimum cache lifetime': \"30m\" (default) or \"12h\". 'Set prompt_cache_breakpoint.ttl to override it for an individual explicit breakpoint. Omitting both settings preserves the default \"30m\" behavior.' The summary of model differences gives the supported values as '\"30m\" (default), or \"12h\" in the Responses API'."
          }
        ]
      },
      "lifetime": {
        "short": {
          "safe_s": 1800,
          "basis": "documented",
          "source": "models.dev",
          "date": "2026-11-17",
          "documented_s": 1800,
          "measured_s": 1800,
          "documented_status": "not_contradicted",
          "clients": 1,
          "evaluations": 1,
          "checks": 16,
          "hits": 10,
          "checks_inside": 10,
          "hits_inside": 10,
          "tested_from_s": 300,
          "first_miss_s": 2400
        },
        "long": {
          "safe_s": 43200,
          "basis": "documented",
          "source": "models.dev",
          "date": "2026-11-17",
          "documented_s": 43200,
          "measured_s": null,
          "documented_status": null,
          "clients": 0,
          "evaluations": 0,
          "checks": 0,
          "hits": 0,
          "checks_inside": null,
          "hits_inside": null,
          "tested_from_s": null,
          "first_miss_s": null
        },
        "lifetimes": [
          {
            "retention_profile": "short",
            "basis": "documented",
            "source": "models.dev",
            "date": "2026-11-17",
            "lifetime_s": 1800,
            "mode": "explicit",
            "documented_as": "30m",
            "client": null,
            "client_label": null,
            "parameter": null,
            "value": null,
            "evaluations": 0,
            "evaluation_ids": [],
            "checks": 0,
            "hits": 0,
            "tested_from_s": null,
            "first_miss_s": null,
            "results": null
          },
          {
            "retention_profile": "short",
            "basis": "measured",
            "source": "providers.dev",
            "date": "2026-11-11",
            "lifetime_s": 1800,
            "mode": null,
            "documented_as": null,
            "client": "cliproxyapi",
            "client_label": "Requests sent through CLIProxyAPI",
            "parameter": null,
            "value": null,
            "evaluations": 1,
            "evaluation_ids": [
              "gpt6-2026-11-11/G6"
            ],
            "checks": 16,
            "hits": 10,
            "tested_from_s": 300,
            "first_miss_s": 2400,
            "results": [
              {
                "kind": "control",
                "age_s": 0,
                "hits": 1,
                "checks": 1,
                "hit_rate_pct": 100
              },
              {
                "kind": "timed",
                "age_s": 300,
                "hits": 3,
                "checks": 3,
                "hit_rate_pct": 100
              },
              {
                "kind": "timed",
                "age_s": 900,
                "hits": 3,
                "checks": 3,
                "hit_rate_pct": 100
              },
              {
                "kind": "timed",
                "age_s": 1800,
                "hits": 3,
                "checks": 3,
                "hit_rate_pct": 100
              },
              {
                "kind": "timed",
                "age_s": 2400,
                "hits": 0,
                "checks": 3,
                "hit_rate_pct": 0
              },
              {
                "kind": "timed",
                "age_s": 3600,
                "hits": 0,
                "checks": 3,
                "hit_rate_pct": 0
              }
            ]
          },
          {
            "retention_profile": "long",
            "basis": "documented",
            "source": "models.dev",
            "date": "2026-11-17",
            "lifetime_s": 43200,
            "mode": "explicit",
            "documented_as": "12h",
            "client": null,
            "client_label": null,
            "parameter": null,
            "value": null,
            "evaluations": 0,
            "evaluation_ids": [],
            "checks": 0,
            "hits": 0,
            "tested_from_s": null,
            "first_miss_s": null,
            "results": null
          }
        ]
      },
      "evaluations": [
        {
          "id": "gpt6-2026-11-11/G6",
          "route": "openai-api",
          "route_label": "OpenAI API key",
          "client": "cliproxyapi",
          "client_label": "Requests sent through CLIProxyAPI",
          "date": "2026-11-11",
          "request_settings": {},
          "retention_profile": "short",
          "parameter": null,
          "value": null,
          "results": [
            {
              "kind": "control",
              "age_s": 0,
              "hits": 1,
              "checks": 1,
              "hit_rate_pct": 100
            },
            {
              "kind": "timed",
              "age_s": 300,
              "hits": 3,
              "checks": 3,
              "hit_rate_pct": 100
            },
            {
              "kind": "timed",
              "age_s": 900,
              "hits": 3,
              "checks": 3,
              "hit_rate_pct": 100
            },
            {
              "kind": "timed",
              "age_s": 1800,
              "hits": 3,
              "checks": 3,
              "hit_rate_pct": 100
            },
            {
              "kind": "timed",
              "age_s": 2400,
              "hits": 0,
              "checks": 3,
              "hit_rate_pct": 0
            },
            {
              "kind": "timed",
              "age_s": 3600,
              "hits": 0,
              "checks": 3,
              "hit_rate_pct": 0
            }
          ],
          "late_excluded": 0,
          "note": null,
          "source": "https://github.com/ngvoicu/groundtruth/blob/main/results/gpt6-2026-11-11/G6-2026-11-11T10-21-23.json"
        }
      ]
    },
    "pricing": {
      "coverage": "partial",
      "billing": "per_use",
      "reference_ref": null,
      "rules": [
        {
          "id": "cost.text.input.price",
          "when": null,
          "meter": "text.input",
          "operation": "set",
          "amount": 10,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.price",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.cache.read",
          "when": null,
          "meter": "text.cache_read",
          "operation": "set",
          "amount": 1,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.cache.read",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.output.price",
          "when": null,
          "meter": "text.output",
          "operation": "set",
          "amount": 50,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.output.price",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.web_search.price",
          "when": null,
          "meter": "web_search",
          "operation": "set",
          "amount": 10,
          "currency": "USD",
          "unit": {
            "name": "search",
            "quantity": 1000
          },
          "applies_to": "all_usage",
          "source_path": "cost.web_search.price",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.cache.write.30m",
          "when": {
            "kind": "predicate",
            "field": "cache.retention_s",
            "op": "eq",
            "value": 1800
          },
          "meter": "text.cache_write",
          "operation": "set",
          "amount": 12.5,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.cache.write.30m",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.cache.write.12h",
          "when": {
            "kind": "predicate",
            "field": "cache.retention_s",
            "op": "eq",
            "value": 43200
          },
          "meter": "text.cache_write",
          "operation": "set",
          "amount": 25,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.cache.write.12h",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.overrides[0].price",
          "when": {
            "kind": "predicate",
            "field": "request.context_tokens",
            "op": "gt",
            "value": 272000
          },
          "meter": "text.input",
          "operation": "set",
          "amount": 20,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.overrides[0].price",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.overrides[0].cache.read",
          "when": {
            "kind": "predicate",
            "field": "request.context_tokens",
            "op": "gt",
            "value": 272000
          },
          "meter": "text.cache_read",
          "operation": "set",
          "amount": 2,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.overrides[0].cache.read",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.overrides[0].cache.write.30m",
          "when": {
            "kind": "all",
            "conditions": [
              {
                "kind": "predicate",
                "field": "request.context_tokens",
                "op": "gt",
                "value": 272000
              },
              {
                "kind": "predicate",
                "field": "cache.retention_s",
                "op": "eq",
                "value": 1800
              }
            ]
          },
          "meter": "text.cache_write",
          "operation": "set",
          "amount": 25,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.overrides[0].cache.write.30m",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.input.overrides[0].cache.write.12h",
          "when": {
            "kind": "all",
            "conditions": [
              {
                "kind": "predicate",
                "field": "request.context_tokens",
                "op": "gt",
                "value": 272000
              },
              {
                "kind": "predicate",
                "field": "cache.retention_s",
                "op": "eq",
                "value": 43200
              }
            ]
          },
          "meter": "text.cache_write",
          "operation": "set",
          "amount": 50,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.input.overrides[0].cache.write.12h",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.text.output.overrides[0].price",
          "when": {
            "kind": "predicate",
            "field": "request.context_tokens",
            "op": "gt",
            "value": 272000
          },
          "meter": "text.output",
          "operation": "set",
          "amount": 75,
          "currency": "USD",
          "unit": {
            "name": "token",
            "quantity": 1000000
          },
          "applies_to": "all_usage",
          "source_path": "cost.text.output.overrides[0].price",
          "period": null,
          "resulting_rates": null
        },
        {
          "id": "cost.multipliers[0].factor.text",
          "when": {
            "kind": "predicate",
            "field": "request.service_tier",
            "op": "eq",
            "value": "priority"
          },
          "meter": "text.*",
          "operation": "multiply",
          "amount": 2,
          "currency": null,
          "unit": null,
          "applies_to": "all_usage",
          "source_path": "cost.multipliers[0].factor.text",
          "period": null,
          "resulting_rates": [
            {
              "meter": "text.input",
              "amount": 20,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.cache_read",
              "amount": 2,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.output",
              "amount": 100,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            }
          ]
        },
        {
          "id": "cost.multipliers[1].factor.text",
          "when": {
            "kind": "predicate",
            "field": "request.service_tier",
            "op": "eq",
            "value": "ultrafast"
          },
          "meter": "text.*",
          "operation": "multiply",
          "amount": 6,
          "currency": null,
          "unit": null,
          "applies_to": "all_usage",
          "source_path": "cost.multipliers[1].factor.text",
          "period": null,
          "resulting_rates": [
            {
              "meter": "text.input",
              "amount": 60,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.cache_read",
              "amount": 6,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.output",
              "amount": 300,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            }
          ]
        },
        {
          "id": "cost.multipliers[2].factor.text",
          "when": {
            "kind": "predicate",
            "field": "request.service_tier",
            "op": "eq",
            "value": "flex"
          },
          "meter": "text.*",
          "operation": "multiply",
          "amount": 0.5,
          "currency": null,
          "unit": null,
          "applies_to": "all_usage",
          "source_path": "cost.multipliers[2].factor.text",
          "period": null,
          "resulting_rates": [
            {
              "meter": "text.input",
              "amount": 5,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.cache_read",
              "amount": 0.5,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.output",
              "amount": 25,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            }
          ]
        },
        {
          "id": "cost.multipliers[3].factor.text",
          "when": {
            "kind": "not",
            "condition": {
              "kind": "predicate",
              "field": "request.region",
              "op": "eq",
              "value": "global"
            }
          },
          "meter": "text.*",
          "operation": "multiply",
          "amount": 1.1,
          "currency": null,
          "unit": null,
          "applies_to": "all_usage",
          "source_path": "cost.multipliers[3].factor.text",
          "period": null,
          "resulting_rates": [
            {
              "meter": "text.input",
              "amount": 11,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.cache_read",
              "amount": 1.1,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            },
            {
              "meter": "text.output",
              "amount": 55,
              "currency": "USD",
              "unit": {
                "name": "token",
                "quantity": 1000000
              }
            }
          ]
        }
      ],
      "rule_order": "listed",
      "unparsed": [],
      "evidence": [
        {
          "kind": "documented",
          "url": "https://models.dev",
          "date": "2026-11-17",
          "note": "The cost models.dev records for this entry. Rules are in the order models.dev applies them: base prices, overrides in their order, then multipliers."
        }
      ]
    },
    "request_controls": {
      "coverage": "partial",
      "items": [
        {
          "id": "cache.retention",
          "support": "supported",
          "when": null,
          "bindings": [
            {
              "location": "body",
              "path": "/prompt_cache_options/ttl",
              "scope": "request"
            },
            {
              "location": "body",
              "path": "/prompt_cache_breakpoint/ttl",
              "scope": "content_block"
            }
          ],
          "options": [
            {
              "value": "30m",
              "attributes": {
                "retention_s": 1800,
                "profile": "short"
              },
              "settings": null,
              "when": null
            },
            {
              "value": "12h",
              "attributes": {
                "retention_s": 43200,
                "profile": "long"
              },
              "settings": null,
              "when": null
            }
          ],
          "default": {
            "value": "30m"
          },
          "conditions": [
            "\"12h\" is documented for the Responses API only."
          ],
          "evidence": [
            {
              "kind": "documented",
              "url": "https://developers.openai.com/api/docs/guides/prompt-caching#cache-lifetime-gpt-5-6-and-later",
              "date": "2026-11-14",
              "note": "GPT-5.6 and later: 'In the Responses API, set prompt_cache_options.ttl to choose the minimum cache lifetime': \"30m\" (default) or \"12h\". 'Set prompt_cache_breakpoint.ttl to override it for an individual explicit breakpoint. Omitting both settings preserves the default \"30m\" behavior.' The summary of model differences gives the supported values as '\"30m\" (default), or \"12h\" in the Responses API'."
            }
          ]
        },
        {
          "id": "service_tier",
          "support": "supported",
          "when": null,
          "bindings": null,
          "options": [
            {
              "value": "flex",
              "attributes": null,
              "settings": null,
              "when": null
            },
            {
              "value": "priority",
              "attributes": null,
              "settings": null,
              "when": null
            },
            {
              "value": "ultrafast",
              "attributes": null,
              "settings": null,
              "when": null
            }
          ],
          "default": null,
          "conditions": [],
          "evidence": [
            {
              "kind": "documented",
              "url": "https://models.dev",
              "date": "2026-11-17",
              "note": "Imported capabilities; corrections are recorded in providers_dev.provenance."
            }
          ]
        }
      ]
    },
    "limits": {
      "measured": [],
      "from_measurement": [],
      "input_window": {
        "tokens": 922000,
        "basis": "documented",
        "bound": "limit",
        "scope": "input",
        "source": "models.dev",
        "date": "2026-11-17",
        "documented_tokens": 922000,
        "documented_field": "limit.input",
        "documented_source": "models.dev",
        "documented_date": "2026-11-17",
        "documented_status": null,
        "measured_tokens": null,
        "measured_bound": null,
        "measured_kind": null,
        "measured_refused": null,
        "measured_date": null,
        "clients": 0,
        "evaluations": 0,
        "measurements": []
      }
    },
    "evidence": [],
    "verified": "2026-11-11"
  }
}