← 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

At a glance
Official price$0.75 / $3.75 per 1M
Cache read $0.075 · Vertex
Lowest paid$0.375 / $1.88
NanoGPT Gateway · 5× spread
Context1,048,576
⚠ Providers report 1,000,000–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImageAudioPDFVideo
Knowledge cutoff2026-03
Released / updated2026-08-13 / 2026-08-13

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

Intelligence56
Value75
Coding76.1
Agentic45.1
Output speed323 tok/s
TTFT15.15 s
Cost per task$0.4022
Value formulaIQ 56 ÷ min blended $0.750 = 75
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
lowIQ 50.9 · 303 tok/s
mediumIQ 53.4 · 317 tok/s
highIQ 56 · 323 tok/s

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

Available at 21 providers21 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPTGateway$0.375$1.88$0.037$0.0211,048,57665,536
OpenRouterGateway$0.375$1.88$0.037$0.0211,048,57665,536
RequestyGateway$0.60$3.00$0.061,048,57665,535
CortecsGateway$0.75$3.75$0.075$0.0381,048,5761,048,576
VertexOfficialFirst-party$0.75$3.75$0.0751,048,57665,536
GoogleOfficialFirst-party$0.75$3.75$0.0751,048,57665,536
CrossModelGateway$0.75$3.75$0.075$0.751,048,57665,536
Merge GatewayGateway$0.75$3.75$0.0751,048,57665,536
AIHubMixGateway$0.75$3.75$0.0751,048,57665,536
Vercel AI GatewayCloud$0.75$3.75$0.0751,000,00065,536

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$128.25
2OpenRouter$128.25
3Requesty$205.20
4Cortecs$256.50
5Vertex · Official$256.50
6Google · Official$256.50
Switch to NanoGPT to save $128.25/mo (50%)
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.pdf34accuracySource ↗
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 = minimaleffort = loweffort = mediumeffort = higheffort = noneeffort = maxbudget_tokens

3 / 21 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input list $0.75Output list $3.75Min blended $0.75

Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-14). Each future sync adds a point, and once accumulated a line is drawn here.