Gemini 4 Carbon
google/gemini-4-carbon1M context Compare →- MedianThe median blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $4.00
- Most expensiveThe highest blended price among comparable offers: one price per provider (its cheapest route), standard tier, current prices only. Priority tiers and prices converted from points are not counted.
- $5.00
- Offers
- 34
- Providers
- 13
Cheapest right now
$3.20 blended / 1M tokens
Not enough history yet · tracking since Nov 10, 2026- in
- $1.60
- out
- $8.00
- Cached input
- $0.08
Below the lab's list price: Resold below the lab's list price (−20% vs lab list price), without a declared discount.
Gemini 4 Carbon: the lowest current price is $3.20 per million tokens (at a 3:1 input:output mix), a price below the lab's list price at AtlasCloud, checked on ; the median of the 11 comparable offers is $4.00.
Listed offers, by price
Comparable offersOther offersSolid steps are comparable offers; dashed steps are the other offers, which are not counted in cheapest, median or most expensive.Official list priceOffers not counted in cheapest, median or most expensive (23)
- $4.00 · Google AI Studio via Eden AI · cannot be designated the cheapest
- $4.00 · Google AI Studio via LLM API · cannot be designated the cheapest
- $4.00 · Google Vertex via Eden AI · cannot be designated the cheapest
- $4.00 · Google Vertex via Eden AI · cannot be designated the cheapest
- $4.00 · Google Vertex via Eden AI · cannot be designated the cheapest
- $4.00 · Google Vertex via LLM API · cannot be designated the cheapest
- $4.00 · Abacus RouteLLM via Abacus RouteLLM · cannot be designated the cheapest
- $4.00 · FastRouter via FastRouter · cannot be designated the cheapest
- $4.00 · Glama via Glama · cannot be designated the cheapest
- $4.00 · Nous Portal via Nous Portal · cannot be designated the cheapest
- $4.00 · OrcaRouter via OrcaRouter · cannot be designated the cheapest
- $4.00 · Google AI Studio via LLM Gateway · another route of the same provider
- $4.00 · Google Vertex via Requesty · another route of the same provider
- $4.00 · Google AI Studio via OpenRouter · another route of the same provider
- $4.43 · Cortecs via Cortecs · cannot be designated the cheapest
- $7.20 · Google via OpenRouter · priority tier
- $7.20 · Google AI Studio via OpenRouter · priority tier
- $8.00 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
- $8.00 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
- $8.80 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
- $8.80 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
- $14.40 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
- $14.40 · Google AI Studio via Kilo Gateway · cannot be designated the cheapest
Cheapest that confirms no training on your prompts. The provider's published policy: prompts are not used for training.
$4.00 blended / 1M tokens
- in
- $2.00
- out
- $10.00
- Cached input
- $0.10
Price drop observed: The blended price is 58% lower than before this drop; possibly temporary. · Price drop observed since Nov 11, 2026
Price historyThe cheapest offer each day, against the lab's official list price when it publishes one. Each day at 00:00 UTC, the offer the API would have selected as the cheapest, with the same exclusions as /cheapest. Blended price, promotions included.
| Day | Cheapest offer | Official list price |
|---|---|---|
| 2026-11-10 | $2.20, Google Vertex | $4.00 |
| 2026-11-11 | $4.00, Google AI Studio | $4.00 |
| 2026-11-12 | $4.00, Google AI Studio | $4.00 |
Cheapest offerOfficial list price
| Rank | Provider · viaYou buy access through an aggregator: one account and one API that forward your requests to other providers. "Via" names the aggregator; the price is the one it charges you. When "via" says "hosted API", no aggregator is involved: the model belongs to a lab and another provider sells it. | Input $/1M | Output $/1M | Blended $/1MA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix. | ContextThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. | ConditionsWhat a provider says about how it handles your data and who can sign up: training on prompts, processing region, sign-up requirements. Each comes from the provider's published documents; when nothing is published, it stays unknown. | Signals | Offer |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.60 | 8.00 | 3.20 · Cheapest right now | 1M | Below the lab's list price: Resold below the lab's list price (−20% vs lab list price), without a declared discount. | |||
| 2 | 2.00 | 10.00 | 4.00 | –Unpublished | Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one | |||
| 3 | 2.00 | 10.00 | 4.00 | 1M | Price drop observed: The blended price is 58% lower than before this drop; possibly temporary. · Price drop observed since Nov 11, 2026 | |||
| 4 | 2.00 | 10.00 | 4.00 | 1M | Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one | Unverified. No public page for this offer: listed, not designated cheapest | ||
| 5 | 2.00 | 10.00 | 4.00 | –Unpublished | Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | ||
| 6 | 2.00 | 10.00 | 4.00 | 1M | European Union | Unverified. No public page for this offer: listed, not designated cheapest | ||
| 7 | 2.00 | 10.00 | 4.00 | 1M | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 8 | 2.00 | 10.00 | 4.00 | 1M | United States | Unverified. No public page for this offer: listed, not designated cheapest | ||
| 9 | 2.00 | 10.00 | 4.00 | –Unpublished | Unverified. The source page shows one price per model, not this seller's: listed, not designated cheapest | |||
| 10 | 2.00 | 10.00 | 4.00 | 1M | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 11 | 2.00 | 10.00 | 4.00 | 1M | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 12 | 2.00 | 10.00 | 4.00 | 1M | Unverified. No public page for this offer: listed, not designated cheapest | |||
| 13 | 2.00 | 10.00 | 4.00 | 1M | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 14 | 2.00 | 10.00 | 4.00 | 1M | Unverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapest | |||
| 15 | 2.00 | 10.00 | 4.00 | –Unpublished | ||||
| 16 | 2.00 | 10.00 | Promo: Promotion announced by LLM Gateway · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 20264.00 | –Unpublished | Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one | Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Nov 12). Offers are ranked with the 5% included. | ||
| 17 | 2.00 | 10.00 | Promo: Promotion announced by LLM Gateway · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 20264.00 | –Unpublished | Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Nov 12). Offers are ranked with the 5% included. | |||
| 18 | 2.00 | 10.00 | 4.00 | 1M | Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included. | |||
| 19 | 2.00 | 10.00 | Promo: Promotion announced by OpenRouter · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 20264.00 | 1M | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included. | |||
| 20 | 2.00 | 10.00 | Promo: Promotion announced by OpenRouter · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 20264.00 | 1M | Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included. | ||
| 21 | 2.20 | 11.00 | 4.40 | 1M | European Union | Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included. | ||
| 22 | 2.20 | 11.00 | 4.40 | 1M | United States | Fee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included. | ||
| 23 | 2.20 | 11.00 | Promo: Promotion announced by OpenRouter · −50% vs its usual price · end date not published4.40 | 1M | United States | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included. | ||
| 24 | 2.20 | 11.00 | Promo: Promotion announced by OpenRouter · −50% vs its usual price · end date not published4.40 | 1M | European Union | Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included. | ||
| 25 | 2.22 | 11.09 | 4.43 | 1M | worldwide | Unverified. No public page for this offer: listed, not designated cheapest |
No training on promptsPrompts may be used for trainingTraining terms not published
backend not named. The router bills this price itself without naming who serves the model.
-
AtlasCloud
hosted APISold by a provider other than the lab that made the model.
- Input$/1M
- 1.60
- Output$/1M
- 8.00
- Context
- 1M
Blended$/1M3.20Training terms not publishedBelow the lab's list price: Resold below the lab's list price (−20% vs lab list price), without a declared discount.
-
Google AI Studio
Google AI Studio
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00Training terms not publishedUnconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one
-
NanoGPT
NanoGPT
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00No training on promptsPrice drop observed: The blended price is 58% lower than before this drop; possibly temporary. · Price drop observed since Nov 11, 2026
-
Google AI Studio
Eden AI
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapestUnconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one
: Eden AI (opens in a new tab)No public price page for this model -
Google AI Studio
LLM API
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00No training on promptsUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapestUnconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one
-
Google Vertex
Eden AI
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingEuropean UnionUnverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab)No public price page for this model -
Google Vertex
Eden AI
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingUnverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab)No public price page for this model -
Google Vertex
Eden AI
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingUnited StatesUnverified. No public page for this offer: listed, not designated cheapest
: Eden AI (opens in a new tab)No public price page for this model -
Google Vertex
LLM API
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00No training on promptsUnverified. The source page shows one price per model, not this seller's: listed, not designated cheapest
-
Abacus RouteLLM
Abacus RouteLLM
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00No training on promptsUnverified. No public page for this offer: listed, not designated cheapest
: Abacus RouteLLM (opens in a new tab)No public price page for this model -
FastRouter
FastRouter
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
Glama
Glama
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00No training on promptsUnverified. No public page for this offer: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
: Glama (opens in a new tab)No public price page for this model -
Nous Portal
Nous Portal
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
OrcaRouter
OrcaRouter
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Training terms not publishedUnverified. Neither seller nor price found on its page for 72 hours: listed, not designated cheapestbackend not named: The router bills this price itself without naming who serves the model.
-
Vercel AI Gateway
Vercel AI Gateway
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00No training on prompts
-
Google AI Studio
LLM Gateway
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00No training on promptsPromo: Promotion announced by LLM Gateway · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 2026Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Nov 12). Offers are ranked with the 5% included.+1Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one
-
Google Vertex
LLM Gateway
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- –Unpublished
Blended$/1M4.00No training on promptsPromo: Promotion announced by LLM Gateway · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 2026Fee 5%: LLM Gateway adds a 5% fee on credit usage, plus 1.5% for cards issued outside the US (read on llmgateway.io/pricing on Nov 12). Offers are ranked with the 5% included.
-
Google Vertex
Requesty
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Prompts may be used for trainingFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Google
OpenRouter
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00Training terms not publishedPromo: Promotion announced by OpenRouter · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Google AI Studio
OpenRouter
- Input$/1M
- 2.00
- Output$/1M
- 10.00
- Context
- 1M
Blended$/1M4.00No training on promptsPromo: Promotion announced by OpenRouter · −50% vs its usual price · Discount shown by the seller, no end date announced, seen on Nov 12, 2026Fee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included.+1Unconfirmed. Last checked 1 November 2026: the last published value, not a confirmed one
-
Google Vertex
Requesty
- Input$/1M
- 2.20
- Output$/1M
- 11.00
- Context
- 1M
Blended$/1M4.40Prompts may be used for trainingEuropean UnionFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Google Vertex
Requesty
- Input$/1M
- 2.20
- Output$/1M
- 11.00
- Context
- 1M
Blended$/1M4.40Prompts may be used for trainingUnited StatesFee 5%: Requesty adds a 5% markup (read on requesty.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Google
OpenRouter
- Input$/1M
- 2.20
- Output$/1M
- 11.00
- Context
- 1M
Blended$/1M4.40Training terms not publishedUnited StatesPromo: Promotion announced by OpenRouter · −50% vs its usual price · end date not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Google
OpenRouter
- Input$/1M
- 2.20
- Output$/1M
- 11.00
- Context
- 1M
Blended$/1M4.40Training terms not publishedEuropean UnionPromo: Promotion announced by OpenRouter · −50% vs its usual price · end date not publishedFee 5.5%: OpenRouter adds a 5.5% fee when you buy credits (read on openrouter.ai/pricing on Nov 12). Offers are ranked with this fee included.
-
Cortecs
Cortecs
- Input$/1M
- 2.22
- Output$/1M
- 11.09
- Context
- 1M
Blended$/1M4.43No training on promptsworldwideUnverified. No public page for this offer: listed, not designated cheapest
: Cortecs (opens in a new tab)No public price page for this model
None of the 25 cheapest offers matches these filters. Show all 34 offers to search them all.
3 flex or batch offers hidden (lower priority, variable latency).
Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.
Monthly cost for your workload
Computed by the API for the three cheapest offers, per 30-day month.- AtlasCloud$216.00per month
- Google AI Studio$270.00per month+$54.00 vs the cheapest
- NanoGPT$270.00per month+$54.00 vs the cheapest
The estimate could not be updated. Try again in a moment.
Compare Gemini 4 Carbon with
Related models
More from Google
Same index family
Use this data
The index is queryable. The API is free to use.curl https://api.inferindex.dev/cheapest?model=google/gemini-4-carbonclaude mcp add --transport http inferindex https://mcp.inferindex.dev/mcp