Switch model

API PRICES

Google · gemini-4-carbon

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 2 / output 10 USD/million tokensGoogle ·
Lowest inference provider (cash)
Not listed
Lowest relay (credit)
24 USD credit/million total tokensapi2.apiaqi.com "gemini-ultra" ·

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

Google · gemini-4-carbon official price: input 2, output 10 USD per million tokens (Google, observed 2026-11-13). Cheapest relay: api2.apiaqi.com, group "gemini-ultra" 24 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-11-13). 147 sites have comparable prices; 485 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Standard processing · Applies until: 2026-11-30 · section: Gemini 4 Carbon · tier: Standard · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared through 2026-11-30 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · lt in one or more queries to Google Search. You will be charged for each individual search query performed. Input price | Not available | $2.00 through November 30, 2026. $4.00 st… · , 2026. $20.00 starting December 1, 2026. Context caching price | Not available | $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit… · hared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5,000 req… · products | Not available | No

Price ranges per million tokens

Official cash prices · Lowest 4 · median 4 · highest 4 · 1 quotes USD / per million tokens

Relay USD credit prices · Lowest 24 · median 24 · highest 24 · 1 quotes USD / per million tokens, site credit

Each quote is blended into one price by this workload: ordinary input 75% · cache read 0% · output 25% · cache write 0%. Only prices in effect now are counted.

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
GoogleStandard2100.1—USD / 1M tokensStandard processing · Applies until: 2026-11-30 · section: Gemini 4 Carbon · tier: Standard · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared through 2026-11-30 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · lt in one or more queries to Google Search. You will be charged for each individual search query performed. Input price | Not available | $2.00 through November 30, 2026. $4.00 st… · , 2026. $20.00 starting December 1, 2026. Context caching price | Not available | $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit… · hared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5,000 req… · products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": "standard",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "tier: Standard",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared through 2026-11-30",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\n\n\n\n\n\n\n  \n\n  * A customer-submitted request to Gemini may resu",
    "lt in one or\n    more queries to Google Search. You will be charged for each individual search\n    query performed.\nInput price | Not available | $2.00 through November 30, 2026.   \n$4.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $10.00 through November 30",
    ", 2026.   \n$20.00 starting December 1, 2026.\nContext caching price | Not available | $0.10 through November 30, 2026.   \n$0.20 starting December 1, 2026.\nImplicit caching only (explicit caching is not supported).\nGrounding with Google Search* | Not available | 5,000 free search requests per month (s",
    "hared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to improve our",
    " products | Not available | No"
  ],
  "effectiveFrom": null,
  "effectiveUntil": "2026-11-30"
}

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.

Other tariffs and prices to review

Official price

ProviderTariffInputOutputCache readCache writeUnitObservedConditions and source
GoogleStandard4200.2—USD / 1M tokensStandard processing · Applies from: 2026-12-01 · section: Gemini 4 Carbon · tier: Standard · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared starting 2026-12-01 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · lt in one or more queries to Google Search. You will be charged for each individual search query performed. Input price | Not available | $2.00 through November 30, 2026. $4.00 st… · , 2026. $20.00 starting December 1, 2026. Context caching price | Not available | $0.10 through November 30, 2026. $0.20 starting December 1, 2026. Implicit caching only (explicit… · hared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5,000 req… · products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [],
  "contextTier": null,
  "processingMode": "standard",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "tier: Standard",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared starting 2026-12-01",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\n\n\n\n\n\n\n  \n\n  * A customer-submitted request to Gemini may resu",
    "lt in one or\n    more queries to Google Search. You will be charged for each individual search\n    query performed.\nInput price | Not available | $2.00 through November 30, 2026.   \n$4.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $10.00 through November 30",
    ", 2026.   \n$20.00 starting December 1, 2026.\nContext caching price | Not available | $0.10 through November 30, 2026.   \n$0.20 starting December 1, 2026.\nImplicit caching only (explicit caching is not supported).\nGrounding with Google Search* | Not available | 5,000 free search requests per month (s",
    "hared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to improve our",
    " products | Not available | No"
  ],
  "effectiveFrom": "2026-12-01",
  "effectiveUntil": null
}

Official source
GoogleBatch150.05—USD / 1M tokensBatch processing · Applies until: 2026-11-30 · tier: Batch · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared through 2026-11-30 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · . $2.00 starting December 1, 2026. Output price (including thinking tokens) | Not available | $5.00 through November 30, 2026. $10.00 starting December 1, 2026. Context caching pr… · xplicit caching is not supported). Used to improve our products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Batch"
  ],
  "contextTier": null,
  "processingMode": "batch",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared through 2026-11-30",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\nInput price | Not available | $1.00 through November 30, 2026",
    ".   \n$2.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $5.00 through November 30, 2026.   \n$10.00 starting December 1, 2026.\nContext caching price | Not available | $0.05 through November 30, 2026.   \n$0.10 starting December 1, 2026.\nImplicit caching only (e",
    "xplicit caching is not supported).\nUsed to improve our products | Not available | No"
  ],
  "effectiveFrom": null,
  "effectiveUntil": "2026-11-30"
}

Official source
GoogleBatch2100.1—USD / 1M tokensBatch processing · Applies from: 2026-12-01 · tier: Batch · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared starting 2026-12-01 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · . $2.00 starting December 1, 2026. Output price (including thinking tokens) | Not available | $5.00 through November 30, 2026. $10.00 starting December 1, 2026. Context caching pr… · xplicit caching is not supported). Used to improve our products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Batch"
  ],
  "contextTier": null,
  "processingMode": "batch",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared starting 2026-12-01",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\nInput price | Not available | $1.00 through November 30, 2026",
    ".   \n$2.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $5.00 through November 30, 2026.   \n$10.00 starting December 1, 2026.\nContext caching price | Not available | $0.05 through November 30, 2026.   \n$0.10 starting December 1, 2026.\nImplicit caching only (e",
    "xplicit caching is not supported).\nUsed to improve our products | Not available | No"
  ],
  "effectiveFrom": "2026-12-01",
  "effectiveUntil": null
}

Official source
GoogleOther tariff150.05—USD / 1M tokensFlex processing · Applies until: 2026-11-30 · tier: Flex · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared through 2026-11-30 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · . $2.00 starting December 1, 2026. Output price (including thinking tokens) | Not available | $5.00 through November 30, 2026. $10.00 starting December 1, 2026. Context caching pr… · xplicit caching is not supported). Used to improve our products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Flex"
  ],
  "contextTier": null,
  "processingMode": "flex",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared through 2026-11-30",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\nInput price | Not available | $1.00 through November 30, 2026",
    ".   \n$2.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $5.00 through November 30, 2026.   \n$10.00 starting December 1, 2026.\nContext caching price | Not available | $0.05 through November 30, 2026.   \n$0.10 starting December 1, 2026.\nImplicit caching only (e",
    "xplicit caching is not supported).\nUsed to improve our products | Not available | No"
  ],
  "effectiveFrom": null,
  "effectiveUntil": "2026-11-30"
}

Official source
GoogleOther tariff2100.1—USD / 1M tokensFlex processing · Applies from: 2026-12-01 · tier: Flex · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared starting 2026-12-01 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · . $2.00 starting December 1, 2026. Output price (including thinking tokens) | Not available | $5.00 through November 30, 2026. $10.00 starting December 1, 2026. Context caching pr… · xplicit caching is not supported). Used to improve our products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Flex"
  ],
  "contextTier": null,
  "processingMode": "flex",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared starting 2026-12-01",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\nInput price | Not available | $1.00 through November 30, 2026",
    ".   \n$2.00 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $5.00 through November 30, 2026.   \n$10.00 starting December 1, 2026.\nContext caching price | Not available | $0.05 through November 30, 2026.   \n$0.10 starting December 1, 2026.\nImplicit caching only (e",
    "xplicit caching is not supported).\nUsed to improve our products | Not available | No"
  ],
  "effectiveFrom": "2026-12-01",
  "effectiveUntil": null
}

Official source
GoogleOther tariff3.6180.18—USD / 1M tokensPriority processing · Applies until: 2026-11-30 · tier: Priority · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared through 2026-11-30 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · lt in one or more queries to Google Search. You will be charged for each individual search query performed. Input price | Not available | $3.60 through November 30, 2026. $7.20 st… · , 2026. $36.00 starting December 1, 2026. Context caching price | Not available | $0.18 through November 30, 2026. $0.36 starting December 1, 2026. Implicit caching only (explicit… · hared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5,000 req… · products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Priority"
  ],
  "contextTier": null,
  "processingMode": "priority",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared through 2026-11-30",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\n\n\n\n\n\n\n  \n\n  * A customer-submitted request to Gemini may resu",
    "lt in one or\n    more queries to Google Search. You will be charged for each individual search\n    query performed.\nInput price | Not available | $3.60 through November 30, 2026.   \n$7.20 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $18.00 through November 30",
    ", 2026.   \n$36.00 starting December 1, 2026.\nContext caching price | Not available | $0.18 through November 30, 2026.   \n$0.36 starting December 1, 2026.\nImplicit caching only (explicit caching is not supported).\nGrounding with Google Search* | Not available | 5,000 free search requests per month (s",
    "hared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to improve our",
    " products | Not available | No"
  ],
  "effectiveFrom": null,
  "effectiveUntil": "2026-11-30"
}

Official source
GoogleOther tariff7.2360.36—USD / 1M tokensPriority processing · Applies from: 2026-12-01 · tier: Priority · section: Gemini 4 Carbon · cacheRead note: Implicit caching only (explicit caching is not supported). · price declared starting 2026-12-01 · declared scoped context: *gemini-4-carbon* Try it in Google AI Studio Our most capable reasoning model, built for complex software engineering, deep mathematical and scientific pr… · up to 1M tokens. Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instr… · lt in one or more queries to Google Search. You will be charged for each individual search query performed. Input price | Not available | $3.60 through November 30, 2026. $7.20 st… · , 2026. $36.00 starting December 1, 2026. Context caching price | Not available | $0.18 through November 30, 2026. $0.36 starting December 1, 2026. Implicit caching only (explicit… · hared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). Grounding with Google Maps | Not available | 5,000 req… · products | Not available | No
Full price conditions
{
  "sourceUnit": null,
  "sourceAmounts": null,
  "conditions": [
    "tier: Priority"
  ],
  "contextTier": null,
  "processingMode": "priority",
  "conditionNotes": [
    "section: Gemini 4 Carbon",
    "cacheRead note: Implicit caching only (explicit caching is not supported).",
    "price declared starting 2026-12-01",
    "declared scoped context: *gemini-4-carbon*\n\n  \n\n  \n  \n  Try it in Google AI Studio\n\n  \n\n  \n\n\n\n\n\nOur most capable reasoning model, built for complex software engineering, deep\nmathematical and scientific problem solving, high factual accuracy, autonomous\nmulti-step agents, and long-decode generation ",
    "up to 1M tokens.\n\n\n  Gemini 4 Carbon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.\n\n\n\n\n\n\n  \n\n  * A customer-submitted request to Gemini may resu",
    "lt in one or\n    more queries to Google Search. You will be charged for each individual search\n    query performed.\nInput price | Not available | $3.60 through November 30, 2026.   \n$7.20 starting December 1, 2026.\nOutput price (including thinking tokens) | Not available | $18.00 through November 30",
    ", 2026.   \n$36.00 starting December 1, 2026.\nContext caching price | Not available | $0.18 through November 30, 2026.   \n$0.36 starting December 1, 2026.\nImplicit caching only (explicit caching is not supported).\nGrounding with Google Search* | Not available | 5,000 free search requests per month (s",
    "hared across all Gemini 3 and newer models),\nthen $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).\nGrounding with Google Maps | Not available | 5,000 requests per month (free, shared across all Gemini 3 and newer models), then $14 / 1,000\nsearch queries.\nUsed to improve our",
    " products | Not available | No"
  ],
  "effectiveFrom": "2026-12-01",
  "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.

Filtering by provider: api2.apiaqi.com

Searching…

Browse all providers
Clear filters

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

Price range: lowest 24 · median 24 · highest 24 (1 quotes, USD credits per million total tokens)

sites have comparable prices147485 sites list this model; approximately 1 operators
Lowest input price12USD credits / 1M
Median of each provider’s lowest price12USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
01api2.apiaqi.comAsk or discussOpen this site's home page ↗ · External site; operator not verifiedCollected:
Collected this cycle
View 1 plans
gemini-ultra
gemini-ultra,约0.3rmb/刀 (Not yet translated)
Operator pending verification
12600.624About the median price
Details
Full prices and sources
How this ranking works

All per-token prices: 128,524 prices from 1,383 sites (about 1,275 companies). 109,485 are ranked, from 1,349 sites (about 1,244 companies); 19,039 more are listed separately and not ranked. Prices collected up to 2026-11-15.

This model has 965 recorded prices; 298 can be compared directly. Not comparable yet: price not parsed yet 280, ratio looks unset 71, billed per request or another unit 14, display unit not confirmed 12, CAPTURE_FRAMEWORK_UNIT_SEMANTICS_NOT_REVIEWED 2. 282 more are tiered by rules and compared on the Tiered prices board

1 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.

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

FAQ

Which API is cheapest for Google · gemini-4-carbon?

api2.apiaqi.com, group "gemini-ultra", 24 USD credit per million total tokens, observed 2026-11-13. 147 sites have comparable prices.

What is the official price for Google · gemini-4-carbon?

Input 2, output 10 USD per million tokens, checked 2026-11-13.

How do I use Google · gemini-4-carbon in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Google · gemini-4-carbon API to Claude Code for me". Install Skill →