LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 4 Carbon

google·google/gemini-4-carbon·GA·Closed·gemini series·NEW
Google's most capable reasoning model for complex software engineering, deep math and science, high factual accuracy, and long-horizon autonomous agents

Specs & pricing

Input / output per 1M tokens
Official price·Google
$2.00 / $10.00
Blended $4.00 · Cache read $0.10
Lowest paid·GoogleFirst-party
$2.00 / $10.00
Blended $4.00 · 2.2× spread
Context
1,048,576
Output limit
32,768
Knowledge cutoff
2026-03
Released / updated
2026-11-10 / 2026-11-10
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImageAudioPDFVideo

Gemini 4 Carbon by google is offered by 24 providers on this page. Its official list price is $2.00 per 1M input tokens and $10.00 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 2.2× across the providers that host it.

Artificial Analysis rates it 60 on the Intelligence Index, with 65.3 for Engineering, its strongest domain. Against its lowest blended price of $4.00 per 1M, that is roughly 15 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 81 tokens per second, with 126.55s to the first token. Running one task of the Artificial Analysis suite costs about $7.7555, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Audio, PDF, and Video. Its training knowledge cuts off at 2026-03.

Quality & performanceArtificial Analysis · Intelligence Index v5 · rep. tier High

Intelligence60
Value15
Engineering65.3
Finance & Accounting62.6
Legal62
Healthcare & Medical56.8
Strategy & Ops60.9
Economics59.6
Output speed81 tok/s
TTFT126.55 s
Cost per task$7.76
Value formulaIQ 60 ÷ min blended $4.000 = 15
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
LowIQ 54.2 · 73 tok/s
MediumIQ 58.3 · 76 tok/s
HighIQ 60 · 81 tok/s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 24 providers24 with public prices

  • ProviderInput / Output
  • GoogleOfficialFirst-party
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 32,768
  • VertexOfficialCloud
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 65,536
  • Merge GatewayGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 65,536
  • Kilo GatewayGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 943,718
  • DevPass (LLM Gateway)Gateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 65,536
  • OfoxGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 65,536
  • OpenRouterGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 943,718
  • LLM GatewayGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 1,048,576
  • LLM GatewayGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 1,048,576
  • RequestyGateway
    $2.00 / $10.00
    Cache read $0.10Context 1,048,576Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
GoogleOfficialFirst-party$2.00$10.00$0.10—1,048,57632,768
VertexOfficialCloud$2.00$10.00$0.10—1,048,57665,536
Merge GatewayGateway$2.00$10.00$0.10—1,048,57665,536
Kilo GatewayGateway$2.00$10.00$0.10$0.191,048,576943,718
DevPass (LLM Gateway)Gateway$2.00$10.00$0.10$0.191,048,57665,536
OfoxGateway$2.00$10.00$0.10—1,048,57665,536
OpenRouterGateway$2.00$10.00$0.10$0.191,048,576943,718
LLM GatewayGateway$2.00$10.00$0.10$0.191,048,5761,048,576
LLM GatewayGateway$2.00$10.00$0.10$0.191,048,5761,048,576
RequestyGateway$2.00$10.00$0.10$2.001,048,57665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = higheffort = noneeffort = max

2 / 24 providers expose no reasoning control (reasoning_options: []).

Audio token pricing9 of 24 providers

ProviderAudio inAudio out
Google$2.001.0×—
Vertex$2.001.0×—
Ofox$2.001.0×—
OpenRouter$2.001.0×—
OpenCode$2.001.0×—
Eden AI$4.001.0×—
Eden AI$4.001.0×—
Eden AI$4.401.0×—
Eden AI$4.401.0×—

Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.

Your usage cost

Common scenarios
1Google · Official$672.00
2Vertex · Official$672.00
3Merge Gateway$672.00
4Kilo Gateway$672.00
5DevPass (LLM Gateway)$672.00
6Ofox$672.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input list $2.00Output list $10.00Min blended $4.00

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-11). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations16 items

HLE-Diamond69.1%
CritPt v2 Hard69.0%
FrontierCode 2.040.6%
Terminal-Bench 4.065.1%
Terminal-Bench-Science64.8%
AutomationBench-AA77.8%
AA-Briefcase1611
GDPval-AA1733
GDP.pdf28.4%
AA-LCR79.3%
MLCR-AA19.4%
AA-Omniscience Index53.5
AA-Omniscience Accuracy58.3%
AA-Omniscience Non-Hallucination88.6%
mka0.5434
vials-aa0.6398

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Gemini 4 Hydrogensame series$1.50 / $7.50Gemini Decision 1same series—Gemini Omni 1.2 Flashsame series—GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40Gemini 4 Argonsame lab$2.00 / $10.00
Data partly from models.dev (MIT) · Google official docs ↗