← Model list

Gemini 3.5 Flash

google·google/gemini-3.5-flash·GA·Closed·gemini-flash series

Fast Gemini model balancing multimodal reasoning, tool use, and cost

At a glance
Official price$1.50 / $9.00 per 1M
Cache read $0.15 · Vertex
Lowest paid$0.186 / $1.11
UnoRouter Gateway · 8.9× spread
Context1,048,576
⚠ Providers report 200,000–1,048,576; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
TextImageAudioVideoPDF
Knowledge cutoff2025-01
Released / updated2026-05-19 / 2026-05-19

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

Intelligence52
Value124
Coding70.1
Agentic39.7
Output speed171 tok/s
TTFT27.29 s
Cost per task$0.6934
Value formulaIQ 52 ÷ min blended $0.418 = 124
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
minimalIQ 35.8 · 154 tok/s
mediumIQ 46.7 · 180 tok/s
highIQ 52 · 171 tok/s

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

Available at 29 providers29 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
UnoRouterGateway$0.186$1.111,048,57665,536
RequestyGateway$1.35$8.10$0.135$1.421,048,57665,535
NanoGPTGateway$1.50$9.00$0.15$0.0831,048,57665,536
VertexOfficialFirst-party$1.50$9.00$0.151,048,57665,536
GoogleOfficialFirst-party$1.50$9.00$0.151,048,57665,536
ImpossiblGateway$1.50$9.00$0.151,048,57665,536
OpenRouterGateway$1.50$9.00$0.15$0.0831,048,57665,536
CrossModelGateway$1.50$9.00$0.15$1.501,048,57665,536
NEAR AI CloudGateway$1.50$9.00$0.151,048,57665,536
Merge GatewayGateway$1.50$9.00$0.151,048,57665,536

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

1UnoRouter$92.85
2Requesty$529.20
3NanoGPT$588.00
4Vertex · Official$588.00
5Google · Official$588.00
6Impossibl$588.00
Switch to UnoRouter to save $495.15/mo (84%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark10 items

NameConditionsScoreMetricSource
Terminal-Benchharness: Terminus-2 · v2.176.2success rateSource ↗
SWE-Bench Provariant: single attempt · dataset: public55.1resolve rateSource ↗
MCP Atlas83.6success rateSource ↗
Toolathlon56.5success rateSource ↗
OSWorld-Verified78.4success rateSource ↗
MMMU Provariant: no tools83.6accuracySource ↗
CharXiv Reasoningvariant: no tools84.2accuracySource ↗
Humanity's Last Examdataset: full set, text + MM40.2accuracySource ↗
ARC-AGI-272.1accuracySource ↗
GDPval-AA1656EloSource ↗

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

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxbudget_tokens ≥ 256 ≤ 24,000effort = minimalToggle (on / off)effort = xhigh

3 / 29 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$9.00$02026-08-052026-08-132026-08-05 · Input list $1.502026-08-06 · Input list $1.502026-08-07 · Input list $1.502026-08-08 · Input list $1.502026-08-09 · Input list $1.502026-08-10 · Input list $1.502026-08-11 · Input list $1.502026-08-12 · Input list $1.502026-08-13 · Input list $1.502026-08-05 · Output list $9.002026-08-06 · Output list $9.002026-08-07 · Output list $9.002026-08-08 · Output list $9.002026-08-09 · Output list $9.002026-08-10 · Output list $9.002026-08-11 · Output list $9.002026-08-12 · Output list $9.002026-08-13 · Output list $9.002026-08-05 · Min blended $0.4182026-08-06 · Min blended $0.4182026-08-07 · Min blended $0.4182026-08-08 · Min blended $0.4182026-08-09 · Min blended $0.4182026-08-10 · Min blended $0.4182026-08-11 · Min blended $0.4182026-08-12 · Min blended $0.4182026-08-13 · Min blended $0.418