LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.7 Flash

google·google/gemini-3.7-flash·GA·Closed·gemini-flash series·NEW
High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning

Gemini 3.7 Flash by google is offered by 25 providers on this page. Public prices are shown for 24 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 NanoGPT at $0.75 / $3.75 per 1M, about 2.0× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Artificial Analysis rates it 56 on the Intelligence Index, with 76.1 for coding and 45.1 for agentic tasks. Against its lowest blended price of $1.50 per 1M, that is roughly 37 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 289 tokens per second, with 10.31s to the first token. Running one task of the Artificial Analysis suite costs about $0.4022, 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, Video, Audio, and PDF. Its training knowledge cuts off at 2026-03.

Specs & pricing

Input / output per 1M tokens
Official price·Vertex
$0.75 / $3.75
Blended $1.50 · Cache read $0.075
Lowest paid·NanoGPTGateway
$0.75 / $3.75
Blended $1.50 · 2× spread
1 more $0 channels
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2026-03
Released / updated
2026-08-13 / 2026-08-13
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImageVideoAudioPDF

Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier high

Intelligence56
Value37
Coding76.1
Agentic45.1
Output speed289 tok/s
TTFT10.31 s
Cost per task$0.4022
Value formulaIQ 56 ÷ min blended $1.500 = 37
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
lowIQ 50.9 · 308 tok/s
mediumIQ 53.4 · 287 tok/s
highIQ 56 · 289 tok/s

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

Available at 25 providers24 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
gemini-3-7-flash
GatewayFree——1,048,57665,536
NanoGPTGateway$0.75$3.75$0.075$0.0421,048,57665,536
VivgridGateway$0.75$3.75$0.075—1,048,57665,536
AIHubMixGateway$0.75$3.75$0.075—1,048,57665,536
VertexOfficialFirst-party$0.75$3.75$0.075—1,048,57665,536
RequestyGateway$0.75$3.75$0.075—1,048,57665,535
CrossModelGateway$0.75$3.75$0.075$0.751,048,57665,536
GoogleOfficialFirst-party$0.75$3.75$0.075—1,048,57665,536
Vercel AI GatewayCloud$0.75$3.75$0.075—1,000,000 ⚠65,536
DevPass (LLM Gateway)Gateway$0.75$3.75$0.075$0.0831,048,57665,536

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.

Your usage cost

1NanoGPT$256.50
2Vivgrid$256.50
3AIHubMix$256.50
4Vertex · Official$256.50
5Requesty$256.50
6CrossModel$256.50

1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.

Switch to NanoGPT to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark6 items

NameConditionsScoreMetricSource
FrontierCodev1.1 Main43.6scoreSource ↗
DeepSWEv1.165.3resolve rateSource ↗
Terminal-Benchv2.185.8accuracySource ↗
AutomationBenchdataset: private set30.4accuracySource ↗
GDP.pdf—34accuracySource ↗
GDM-MRCRvariant: 128k average, 8-needle · vv297accuracySource ↗

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

Reasoning control

effort = loweffort = mediumeffort = higheffort = minimaleffort = noneeffort = maxbudget_tokens

3 / 25 providers expose no reasoning control (reasoning_options: []).

Related models

Gemini 3.8 Flashsame series$0.75 / $3.75Gemini 3.8 Flash (EU)same series$0.825 / $4.13Gemini 3.8 Flash (Vertex AI, US)same series$0.75 / $3.75DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Procheaper alternative$0.435 / $0.87GLM-5.3-Flashcheaper alternative$0.075 / $0.25DeepSeek V4 Flash 0731cheaper alternative$0.445 / $1.34

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.75$02026-08-142026-09-032026-08-14 · Input list $0.752026-09-03 · Input list $0.752026-08-14 · Output list $3.752026-09-03 · Output list $3.752026-08-14 · Min blended $0.752026-09-03 · Min blended $1.50
Data partly from models.dev (MIT) · Vertex official docs ↗