LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.6 Flash

google·google/gemini-3.6-flash·GA·Closed·gemini-flash series
Fast Gemini model balancing multimodal reasoning, tool use, and cost

Specs & pricing

Input / output per 1M tokens
Official price·Google
$0.75 / $3.75
Blended $1.50 · Cache read $0.075
Lowest paid·KenariGateway
$0.34 / $1.71
Blended $0.68 · 4.4× spread
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2026-03
Released / updated
2026-07-21 / 2026-07-21
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDFAudioVideo

Gemini 3.6 Flash by google is offered by 36 providers on this page. Public prices are shown for 35 of them. Its official list price is $0.75 per 1M input tokens and $3.75 per 1M output tokens. The lowest paid channel is Kenari at $0.343 / $1.71 per 1M, about 2.2× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 191 tokens per second, with 15.01s to the first token.

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, PDF, Audio, and Video. Its training knowledge cuts off at 2026-03.

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

Intelligence—
Value—
Output speed191 tok/s
TTFT15.01 s

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

Available at 36 providers35 with public prices

  • ProviderInput / Output
  • KenariGateway
    gemini-3-6-flash
    $0.34 / $1.71
    Cache read $0.034Context 1,048,576Output limit 65,536deprecated
  • Kilo GatewayGateway
    $0.38 / $1.88
    Cache read $0.038Context 1,048,576Output limit 65,536
  • VertexOfficialCloud
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536deprecated
  • GoogleOfficialFirst-party
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • CrossModelGateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • NanoGPTGateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • DevPass (LLM Gateway)Gateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
  • OpenRouterGateway
    $0.75 / $3.75
    Cache read $0.075Context 1,048,576Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
gemini-3-6-flash
Gateway$0.34$1.71$0.034$0.0171,048,57665,536deprecated
Kilo GatewayGateway$0.38$1.88$0.038$0.0211,048,57665,536
VertexOfficialCloud$0.75$3.75$0.075—1,048,57665,536deprecated
GoogleOfficialFirst-party$0.75$3.75$0.075—1,048,57665,536
CrossModelGateway$0.75$3.75$0.075$0.751,048,57665,536
LLM GatewayGateway$0.75$3.75$0.075$0.0831,048,57665,536
LLM GatewayGateway$0.75$3.75$0.075$0.0831,048,57665,536
NanoGPTGateway$0.75$3.75$0.075$0.0421,048,57665,536
DevPass (LLM Gateway)Gateway$0.75$3.75$0.075$0.0831,048,57665,536
OpenRouterGateway$0.75$3.75$0.075$0.0421,048,57665,536

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 = minimaleffort = loweffort = mediumeffort = highToggle (on / off)budget_tokens ≥ 256 ≤ 32,000effort = noneeffort = max

1 / 36 providers expose no reasoning control (reasoning_options: []).

Audio token pricing11 of 36 providers

ProviderAudio inAudio out
Vertex$0.751.0×—
Google$0.751.0×—
OpenRouter$0.751.0×—
AIHubMix$0.751.0×—
Eden AI$0.751.0×—
Eden AI$0.751.0×—
Ofox$0.751.0×—
OpenCode$0.751.0×—
Eden AI$0.831.0×—
Eden AI$0.831.0×—
Neon$1.501.0×—

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
1Kenari$117.05
2Kilo Gateway$128.25
3Vertex · Official$256.50
4Google · Official$256.50
5CrossModel$256.50
6LLM Gateway$256.50
Switch to Kenari to save $139.45/mo (54%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$7.50$02026-08-052026-11-17
2026-11-17Input list $0.75Output list $3.75Min blended $0.68

Benchmark10 items

NameConditionsScoreMetricSource
SWE-Bench Proharness: Antigravity58.7resolve rateSource ↗
DeepSWEvariant: high reasoning · v1.149resolve rateSource ↗
Terminal-Benchharness: Terminus 2 · v2.178accuracySource ↗
MLE-Benchdataset: Partial 3063.9average position scoreSource ↗
GDPval-AAvv21421EloSource ↗
OSWorld-Verified—83success rateSource ↗
CharXiv Reasoningvariant: no tools85.2accuracySource ↗
CharXiv Reasoningvariant: with tools89.4accuracySource ↗
GDM-MRCRvariant: 128k average, 8-needle · vv291.8accuracySource ↗
GDM-MRCRvariant: 1M pointwise, 8-needle · vv254accuracySource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Nano Banana 2.1same series$1.50 / $7.50Gemini 3.8 Flash TTSsame series—Gemini 3.8 Livesame series—GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GPT-5.6 Lunacheaper alternative$0.20 / $1.20MiniMax-M3cheaper alternative$0.30 / $1.20Gemini 3.5 Flash Litesame lab$0.30 / $2.50Gemini 3.7 Flashsame lab$0.75 / $3.75

Related articles

  • What is Gemini Spark? Google's 24/7 agent, now Task in Gemini →
Data partly from models.dev (MIT) · Google official docs ↗