Switch model

Search modelsModel640 matches; choose and submit to view prices.

API PRICES

OpenAI · gpt-6-astra

Provider prices, cheapest first

Price comparison

Official (cash): Input 10 / output 50 USD/million tokensOpenAI · 10-24
Lowest inference provider (cash): Input 10 / output 50 USD/million tokensOpenRouter · Aggregator · 10-24
Lowest relay (credit): 26.2 USD credit/million total tokensyfy.zhouyang168.top "Codex8" · 10-23

Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.

All official and inference price observations

OpenAI · gpt-6-astra official price: input 10, output 50 USD per million tokens (OpenAI, observed 2026-10-24). Cheapest inference provider: OpenRouter, input 10, output 50 USD per million tokens. Cheapest relay: yfy.zhouyang168.top, group "Codex8" 26.2 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 180 sites have comparable prices; 951 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Context tier: SHORT_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens · Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Price ranges per million tokens

Official cash prices · Lowest 20 · median 26.875 · highest 33.75 · 2 quotes USD / per million tokens

Inference provider cash prices · Lowest 20 · median 20 · highest 20 · 1 quotes USD / per million tokens

Relay USD credit prices · Lowest 26.2 · median 71 · highest 107.4 · 8 quotes USD / per million tokens, site credit

Official price

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
OpenAI	Standard	10	50	1	30m: 12.5 12h: 25	USD / 1M tokens	2026-10-24	Context tier: SHORT_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [], "contextTier": "SHORT_CONTEXT", "processingMode": "standard", "conditionNotes": [ "documentSection: Flagship models", "processingMode: standard", "promptLength: ≤272K input tokens", "cacheWrite TTL 30m: 12.50 USD per 1M tokens", "cacheWrite TTL 12h: 25.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Standard	20	75	2	30m: 25 12h: 50	USD / 1M tokens	2026-10-24	Context tier: LONG_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: >272K input tokens · cacheWrite TTL 30m: 25.00 USD per 1M tokens · cacheWrite TTL 12h: 50.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [], "contextTier": "LONG_CONTEXT", "processingMode": "standard", "conditionNotes": [ "documentSection: Flagship models", "processingMode: standard", "promptLength: >272K input tokens", "cacheWrite TTL 30m: 25.00 USD per 1M tokens", "cacheWrite TTL 12h: 50.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Provider

Tariff

Input

Output

Cache read

Cache write

Unit

Observed

Conditions and source

OpenAI

Standard

30m: 12.5

12h: 25

USD / 1M tokens

2026-10-24

Context tier: SHORT_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens

Full price conditions

{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "SHORT_CONTEXT",
  "processingMode": "standard",
  "conditionNotes": [
    "documentSection: Flagship models",
    "processingMode: standard",
    "promptLength: ≤272K input tokens",
    "cacheWrite TTL 30m: 12.50 USD per 1M tokens",
    "cacheWrite TTL 12h: 25.00 USD per 1M tokens"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

OpenAI

Standard

30m: 25

12h: 50

USD / 1M tokens

2026-10-24

Context tier: LONG_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: >272K input tokens · cacheWrite TTL 30m: 25.00 USD per 1M tokens · cacheWrite TTL 12h: 50.00 USD per 1M tokens

Full price conditions

{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": "LONG_CONTEXT",
  "processingMode": "standard",
  "conditionNotes": [
    "documentSection: Flagship models",
    "processingMode: standard",
    "promptLength: >272K input tokens",
    "cacheWrite TTL 30m: 25.00 USD per 1M tokens",
    "cacheWrite TTL 12h: 50.00 USD per 1M tokens"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.

Inference providers

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source	vs official
OpenRouter · Aggregator	Standard	10	50	1	12.5	USD / 1M tokens	2026-10-24	Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000001", "cacheWrite": "0.0000125", "input": "0.00001", "output": "0.00005" }, "conditions": [], "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Provider

Tariff

Input

Output

Cache read

Cache write

Unit

Observed

Conditions and source

vs official

OpenRouter · Aggregator

Standard

12.5

USD / 1M tokens

2026-10-24

Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Full price conditions

{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000001",
    "cacheWrite": "0.0000125",
    "input": "0.00001",
    "output": "0.00005"
  },
  "conditions": [],
  "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Other tariffs and prices to review

Official price

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
OpenAI	Batch	5	25	0.5	30m: 6.25 12h: 12.5	USD / 1M tokens	2026-10-24	Context tier: SHORT_CONTEXT · Batch processing · processingMode: batch · documentSection: Flagship models · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 6.25 USD per 1M tokens · cacheWrite TTL 12h: 12.50 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: batch" ], "contextTier": "SHORT_CONTEXT", "processingMode": "batch", "conditionNotes": [ "documentSection: Flagship models", "promptLength: ≤272K input tokens", "cacheWrite TTL 30m: 6.25 USD per 1M tokens", "cacheWrite TTL 12h: 12.50 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Batch	10	37.5	1	30m: 12.5 12h: 25	USD / 1M tokens	2026-10-24	Context tier: LONG_CONTEXT · Batch processing · processingMode: batch · documentSection: Flagship models · promptLength: >272K input tokens · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: batch" ], "contextTier": "LONG_CONTEXT", "processingMode": "batch", "conditionNotes": [ "documentSection: Flagship models", "promptLength: >272K input tokens", "cacheWrite TTL 30m: 12.50 USD per 1M tokens", "cacheWrite TTL 12h: 25.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	5	25	0.5	30m: 6.25 12h: 12.5	USD / 1M tokens	2026-10-24	Context tier: SHORT_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 6.25 USD per 1M tokens · cacheWrite TTL 12h: 12.50 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "SHORT_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: ≤272K input tokens", "cacheWrite TTL 30m: 6.25 USD per 1M tokens", "cacheWrite TTL 12h: 12.50 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	10	37.5	1	30m: 12.5 12h: 25	USD / 1M tokens	2026-10-24	Context tier: LONG_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: >272K input tokens · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "LONG_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: >272K input tokens", "cacheWrite TTL 30m: 12.50 USD per 1M tokens", "cacheWrite TTL 12h: 25.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	20	100	2	30m: 25 12h: 50	USD / 1M tokens	2026-10-24	Context tier: SHORT_CONTEXT · Fast processing · processingMode: fast · documentSection: Flagship models · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 25.00 USD per 1M tokens · cacheWrite TTL 12h: 50.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: fast" ], "contextTier": "SHORT_CONTEXT", "processingMode": "fast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: ≤272K input tokens", "cacheWrite TTL 30m: 25.00 USD per 1M tokens", "cacheWrite TTL 12h: 50.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	40	150	4	30m: 50 12h: 100	USD / 1M tokens	2026-10-24	Context tier: LONG_CONTEXT · Fast processing · processingMode: fast · documentSection: Flagship models · promptLength: >272K input tokens · cacheWrite TTL 30m: 50.00 USD per 1M tokens · cacheWrite TTL 12h: 100.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: fast" ], "contextTier": "LONG_CONTEXT", "processingMode": "fast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: >272K input tokens", "cacheWrite TTL 30m: 50.00 USD per 1M tokens", "cacheWrite TTL 12h: 100.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	60	300	6	30m: 75 12h: 150	USD / 1M tokens	2026-10-24	Context tier: SHORT_CONTEXT · Ultrafast processing · processingMode: ultrafast · documentSection: Flagship models · promptLength: ≤272K input tokens · cacheWrite TTL 30m: 75.00 USD per 1M tokens · cacheWrite TTL 12h: 150.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: ultrafast" ], "contextTier": "SHORT_CONTEXT", "processingMode": "ultrafast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: ≤272K input tokens", "cacheWrite TTL 30m: 75.00 USD per 1M tokens", "cacheWrite TTL 12h: 150.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	120	450	12	30m: 150 12h: 300	USD / 1M tokens	2026-10-24	Context tier: LONG_CONTEXT · Ultrafast processing · processingMode: ultrafast · documentSection: Flagship models · promptLength: >272K input tokens · cacheWrite TTL 30m: 150.00 USD per 1M tokens · cacheWrite TTL 12h: 300.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: ultrafast" ], "contextTier": "LONG_CONTEXT", "processingMode": "ultrafast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: >272K input tokens", "cacheWrite TTL 30m: 150.00 USD per 1M tokens", "cacheWrite TTL 12h: 300.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Standard	10	50	1	30m: 12.5 12h: 25	USD / 1M tokens	2026-10-24	Context tier: CONTEXT_SELECTION_NOT_RETAINED · Standard processing · selected context not retained in HTML public projection · documentSection: Flagship models · processingMode: standard · cacheWrite TTL 30m: 12.50 USD per 1M tokens · cacheWrite TTL 12h: 25.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "selected context not retained in HTML public projection" ], "contextTier": "CONTEXT_SELECTION_NOT_RETAINED", "processingMode": "standard", "conditionNotes": [ "documentSection: Flagship models", "processingMode: standard", "cacheWrite TTL 30m: 12.50 USD per 1M tokens", "cacheWrite TTL 12h: 25.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Batch	5	25	0.5	30m: 6.25 12h: 12.5	USD / 1M tokens	2026-10-24	Context tier: CONTEXT_SELECTION_NOT_RETAINED · Batch processing · processingMode: batch · selected context not retained in HTML public projection · documentSection: Flagship models · cacheWrite TTL 30m: 6.25 USD per 1M tokens · cacheWrite TTL 12h: 12.50 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: batch", "selected context not retained in HTML public projection" ], "contextTier": "CONTEXT_SELECTION_NOT_RETAINED", "processingMode": "batch", "conditionNotes": [ "documentSection: Flagship models", "cacheWrite TTL 30m: 6.25 USD per 1M tokens", "cacheWrite TTL 12h: 12.50 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	20	100	2	30m: 25 12h: 50	USD / 1M tokens	2026-10-24	Context tier: CONTEXT_SELECTION_NOT_RETAINED · Fast processing · processingMode: fast · selected context not retained in HTML public projection · documentSection: Flagship models · cacheWrite TTL 30m: 25.00 USD per 1M tokens · cacheWrite TTL 12h: 50.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: fast", "selected context not retained in HTML public projection" ], "contextTier": "CONTEXT_SELECTION_NOT_RETAINED", "processingMode": "fast", "conditionNotes": [ "documentSection: Flagship models", "cacheWrite TTL 30m: 25.00 USD per 1M tokens", "cacheWrite TTL 12h: 50.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	60	300	6	30m: 75 12h: 150	USD / 1M tokens	2026-10-24	Context tier: CONTEXT_SELECTION_NOT_RETAINED · Ultrafast processing · processingMode: ultrafast · selected context not retained in HTML public projection · documentSection: Flagship models · cacheWrite TTL 30m: 75.00 USD per 1M tokens · cacheWrite TTL 12h: 150.00 USD per 1M tokens Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: ultrafast", "selected context not retained in HTML public projection" ], "contextTier": "CONTEXT_SELECTION_NOT_RETAINED", "processingMode": "ultrafast", "conditionNotes": [ "documentSection: Flagship models", "cacheWrite TTL 30m: 75.00 USD per 1M tokens", "cacheWrite TTL 12h: 150.00 USD per 1M tokens" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	5	25	0.5	6.25	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "SHORT_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	10	37.5	1	12.5	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "LONG_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Inference providers

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
OpenRouter · Aggregator	Standard	20	75	2	25	USD / 1M tokens	2026-10-24	Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000002", "cacheWrite": "0.000025", "input": "0.00002", "output": "0.000075" }, "conditions": [ "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)" ], "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenRouter · Aggregator	Batch	5	25	0.5	6.25	USD / 1M tokens	2026-10-24	Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · OpenRouter batch variant · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.0000005", "cacheWrite": "0.00000625", "input": "0.000005", "output": "0.000025" }, "conditions": [ "OpenRouter batch variant" ], "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenRouter · Aggregator	Batch	10	37.5	1	12.5	USD / 1M tokens	2026-10-24	Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter batch variant · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000001", "cacheWrite": "0.0000125", "input": "0.00001", "output": "0.0000375" }, "conditions": [ "OpenRouter batch variant", "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)" ], "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Provider

Tariff

Input

Output

Cache read

Cache write

Unit

Observed

Conditions and source

OpenRouter · Aggregator

Standard

USD / 1M tokens

2026-10-24

Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Full price conditions

{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000002",
    "cacheWrite": "0.000025",
    "input": "0.00002",
    "output": "0.000075"
  },
  "conditions": [
    "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)"
  ],
  "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

OpenRouter · Aggregator

Batch

0.5

6.25

USD / 1M tokens

2026-10-24

Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · OpenRouter batch variant · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Full price conditions

{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.0000005",
    "cacheWrite": "0.00000625",
    "input": "0.000005",
    "output": "0.000025"
  },
  "conditions": [
    "OpenRouter batch variant"
  ],
  "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

OpenRouter · Aggregator

Batch

37.5

12.5

USD / 1M tokens

2026-10-24

Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter batch variant · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter)

Full price conditions

{
  "sourceUnit": "USD_PER_TOKEN",
  "sourceAmounts": {
    "cacheRead": "0.000001",
    "cacheWrite": "0.0000125",
    "input": "0.00001",
    "output": "0.0000375"
  },
  "conditions": [
    "OpenRouter batch variant",
    "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)"
  ],
  "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000",
  "processingMode": null,
  "conditionNotes": [
    "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)"
  ],
  "effectiveFrom": null,
  "effectiveUntil": null
}

Official source

Older official and inference provider prices

Earlier price observations and their original conditions

Official price

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
OpenAI	Batch	5	25	0.5	6.25	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Batch processing · processingMode: batch · documentSection: Flagship models · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: batch" ], "contextTier": "SHORT_CONTEXT", "processingMode": "batch", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	5	25	0.5	6.25	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "SHORT_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Batch	10	37.5	1	12.5	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Batch processing · processingMode: batch · documentSection: Flagship models · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: batch" ], "contextTier": "LONG_CONTEXT", "processingMode": "batch", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	10	37.5	1	12.5	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Flex processing · processingMode: flex · documentSection: Flagship models · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: flex" ], "contextTier": "LONG_CONTEXT", "processingMode": "flex", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Standard	10	50	1	12.5	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [], "contextTier": "SHORT_CONTEXT", "processingMode": "standard", "conditionNotes": [ "documentSection: Flagship models", "processingMode: standard", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Standard	20	75	2	25	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Standard processing · documentSection: Flagship models · processingMode: standard · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [], "contextTier": "LONG_CONTEXT", "processingMode": "standard", "conditionNotes": [ "documentSection: Flagship models", "processingMode: standard", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	20	100	2	25	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Fast processing · processingMode: fast · documentSection: Flagship models · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: fast" ], "contextTier": "SHORT_CONTEXT", "processingMode": "fast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	40	150	4	50	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Fast processing · processingMode: fast · documentSection: Flagship models · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: fast" ], "contextTier": "LONG_CONTEXT", "processingMode": "fast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	60	300	6	75	USD / 1M tokens	2026-10-17	Context tier: SHORT_CONTEXT · Ultrafast processing · processingMode: ultrafast · documentSection: Flagship models · promptLength: Short context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: ultrafast" ], "contextTier": "SHORT_CONTEXT", "processingMode": "ultrafast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Short context" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenAI	Other tariff	120	450	12	150	USD / 1M tokens	2026-10-17	Context tier: LONG_CONTEXT · Ultrafast processing · processingMode: ultrafast · documentSection: Flagship models · promptLength: Long context Full price conditions { "sourceUnit": null, "sourceAmounts": null, "conditions": [ "processingMode: ultrafast" ], "contextTier": "LONG_CONTEXT", "processingMode": "ultrafast", "conditionNotes": [ "documentSection: Flagship models", "promptLength: Long context" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Inference providers

Provider	Tariff	Input	Output	Cache read	Cache write	Unit	Observed	Conditions and source
OpenRouter · Aggregator	Batch	5	25	0.5	6.25	USD / 1M tokens	2026-10-17	Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · OpenRouter batch variant · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.0000005", "cacheWrite": "0.00000625", "input": "0.000005", "output": "0.000025" }, "conditions": [ "OpenRouter batch variant" ], "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenRouter · Aggregator	Batch	10	37.5	1	12.5	USD / 1M tokens	2026-10-17	Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter batch variant · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000001", "cacheWrite": "0.0000125", "input": "0.00001", "output": "0.0000375" }, "conditions": [ "OpenRouter batch variant", "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)" ], "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenRouter · Aggregator	Standard	10	50	1	12.5	USD / 1M tokens	2026-10-17	Context tier: OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000001", "cacheWrite": "0.0000125", "input": "0.00001", "output": "0.00005" }, "conditions": [], "contextTier": "OPENROUTER_DEFAULT_WHEN_NO_OVERRIDE", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source
OpenRouter · Aggregator	Standard	20	75	2	25	USD / 1M tokens	2026-10-17	Context tier: OPENROUTER_MIN_PROMPT_TOKENS_272000 · OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated) · Additional web_search price 0.01 USD (per unit as declared by OpenRouter) Full price conditions { "sourceUnit": "USD_PER_TOKEN", "sourceAmounts": { "cacheRead": "0.000002", "cacheWrite": "0.000025", "input": "0.00002", "output": "0.000075" }, "conditions": [ "OpenRouter override for prompts from 272000 tokens (boundary inclusivity not stated)" ], "contextTier": "OPENROUTER_MIN_PROMPT_TOKENS_272000", "processingMode": null, "conditionNotes": [ "Additional web_search price 0.01 USD (per unit as declared by OpenRouter)" ], "effectiveFrom": null, "effectiveUntil": null } Official source

Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest 26.2 · median 71 · highest 107.4 (8 quotes, USD credits per million total tokens)

sites have comparable prices180951 sites list this model; approximately 1 operators

Lowest input price13.1USD credits / 1M

Median of each provider’s lowest price13.1USD credits / 1M

Relays

Prices below are in site credit, not cash.

#	Provider	Plan / conditions	Input ↑USD credits / 1M	Output USD credits / 1M	Cache readUSD credits / 1M	BlendedUSD credits / 1M	Details
Recent price
01	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex8 Low-price plus+K12 mixed account pool-poor stability-corresponds to 0.035x rate multiplier [machine translation]Original: 低价plus+K12混池-稳定性差-对应0.035倍率 Operator pending verification	13.1	65.5	2.62	26.2Median price ÷ this price: 2.7×	Full prices and sources
02	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex10 plus account pool-poor stability-corresponds to 0.06 rate multiplier [machine translation]Original: plus号池-稳定性差-对应0.06倍率 Operator pending verification	14.9	74.5	2.98	29.8Median price ÷ this price: 2.4×	Full prices and sources
03	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex Plus account pool-stable plus account pool-corresponds to 0.09 rate multiplier [machine translation]Original: Plus号池-稳定plus号池-对应0.09倍率 Operator pending verification	32.3	161.5	6.46	64.6Median price ÷ this price: 1.1×	Full prices and sources
04	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex7 Pro account pool-may be dumbed down-corresponds to 0.09x rate multiplier [machine translation]Original: Pro号池-可能会降智-对应0.09倍率 Operator pending verification	33.6	168	6.72	67.2Median price ÷ this price: 1.1×	Full prices and sources
05	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex6 Pro account pool-may be dumbed down-corresponds to 0.10 rate multiplier [machine translation]Original: Pro号池-可能会降智-对应0.10倍率 Operator pending verification	37.4	187	7.48	74.8Median price ÷ this price: 0.9×	Full prices and sources
06	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex4 Pro account pool-premium quality, not dumbed down-corresponds to 0.126 rate multiplier [machine translation]Original: Pro号池-高质量不降智-对应0.126倍率 Operator pending verification	47.1	235.5	9.42	94.2Median price ÷ this price: 0.8×	Full prices and sources
07	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex5 Pro account pool-not dumbed down-corresponds to 0.132 rate multiplier [machine translation]Original: Pro号池-不降智-对应0.132倍率 Operator pending verification	49.3	246.5	9.86	98.6Median price ÷ this price: 0.7×	Full prices and sources
08	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex2 Plus+Pro mixed pool-latency a bit high-corresponds to 0.143 rate multiplier [machine translation]Original: Plus+Pro混池-延迟有点高-对应0.143倍率 Operator pending verification	53.7	268.5	10.74	107.4Median price ÷ this price: 0.7×	Full prices and sources
Flagged · not ranked · Recent price
—	yfy.zhouyang168.topAsk or discussCollected: 23 Oct 2026, 23:51 UTC Collected this cycle View 9 plans 1 more site of the same company nty-hk.zhouyang168.top Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.	Codex9 Pro account pool-premium quality, not dumbed down-corresponds to 0.21 rate multiplier [machine translation]Original: Pro号池-高质量不降智-对应0.21倍率 Note: far from other providers’ prices. This price is not ranked or counted. Operator pending verification	78.4	392	15.68	156.8Median price ÷ this price: 0.5×	Full prices and sources

Special groups · 7 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

near-zero-ratio group: 5 rows
top-up or membership gated: 1 rows
unrecognized flag USAGE_IMAGE_ONLY: 1 rows

apiroute.top · gpt-plus · gpt-6-astra · Input 0.135 / Output 0.675 USD credits / 1M
apiroute.top · gpt-pro · gpt-6-astra · Input 0.22 / Output 1.1 USD credits / 1M
bmodels.top · default · gpt-6-astra · Input 0.3 / Output 1.5 USD credits / 1M
newtonrouter.com · Gpt Pro 20x · gpt-6-astra · Input 0.35 / Output 1.75 USD credits / 1M
cc.kakade.top · Codex-vip-stable group [machine translation]Group on site: Codex-vip-稳定组 · gpt-6-astra · Input 6 / Output 36 USD credits / 1M
new.api.yynanshen.top · image · gpt-6-astra · Input 10 / Output 50 USD credits / 1M
api.edu9.us · shareVIP-only codex [machine translation]Group on site: shareVIP专用codex · gpt-6-astra · Input 20 / Output 100 USD credits / 1M

View all 7 rows →

Related variants · 4 rows · not ranked

These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.

gpt-6-astra[1m] ([1m] · context or size tier (e.g. 128k, 1M, 4K)): 4 rows

api.bddevlab.online · CLAUDE-FABLE · gpt-6-astra[1m] · Input 4 / Output 4 USD credits / 1M
api.bddevlab.online · CodexDeepSeek · gpt-6-astra[1m] · Input 5.8744 / Output 5.8744 USD credits / 1M
api.bddevlab.online · default · gpt-6-astra[1m] · Input 6.7136 / Output 6.7136 USD credits / 1M
api.bddevlab.online · CLAUDE-HIGH-UPTIME · gpt-6-astra[1m] · Input 11.413 / Output 11.413 USD credits / 1M

View all 4 rows →

How this ranking works

All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.

This model has 3812 recorded prices; 550 can be compared directly (534 ranked, 16 listed separately). Not comparable yet: tiered by rules (see Tiered prices) 2129, price not parsed yet 721, new price under review; showing the previous one 198, ratio looks unset 99, display unit not confirmed 45, scope of the official doc price not confirmed 24, billed per request or another unit 20

9 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.

Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.

“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.

Full methodology →

Sources not accepted this cycle and reasons

Manufacturer documentation and lifecycle

These manufacturer statements do not verify relay backends, availability, GPU ownership or cash eligibility. Aliases are never merged automatically.

Latest generation in documentation · GPT Astra

GPT-6 Astra · gpt-6-astra

Documentation checked: 2026-10-23T21:48:25.843Z · 2026-10-23T21:48:28.294Z

Manufacturer documentation evidence · 4i:openai-astra · 2026-10-19T02:22:59.275558+00:00
Manufacturer documentation evidence · 4i:openai-models · 2026-10-19T02:22:59.276588+00:00
Manufacturer documentation evidence · w43-targeted:openai-astra · 2026-10-23T21:48:25.843Z
Manufacturer documentation evidence · w43-targeted:openai-models · 2026-10-23T21:48:28.294Z

Download complete public documentation archive, including unmatched items

FAQ

Which API is cheapest for OpenAI · gpt-6-astra?

yfy.zhouyang168.top, group "Codex8", 26.2 USD credit per million total tokens, observed 2026-10-23. 180 sites have comparable prices.

What is the official price for OpenAI · gpt-6-astra?

Input 10, output 50 USD per million tokens, checked 2026-10-24. Lowest inference provider: OpenRouter, input 10, output 50 USD per million tokens.

How do I use OpenAI · gpt-6-astra in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest OpenAI · gpt-6-astra API to Claude Code for me". Install Skill →