← Model list

Gemini 2.5 Flash

google·google/gemini-2.5-flash·GA·Closed·gemini-flash series

Fast Gemini workhorse for multimodal apps where latency and price matter

At a glance
Official price$0.30 / $2.50 per 1M
Cache read $0.03 · Vertex
Lowest paid$0.09 / $0.71
QiHang Gateway · 3.3× spread
1 more $0 channels
Context1,048,576
⚠ Providers report 1,000,000–1,065,535; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageAudioVideoPDF
Knowledge cutoff2025-01
Released / updated2025-06-17 / 2025-06-17

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

Intelligence20.3
Value83
Coding
Agentic
Output speed225 tok/s
TTFT19.09 s
Value formulaIQ 20.3 ÷ min blended $0.245 = 83
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 14.2 · 200 tok/s
ReasoningIQ 20.3 · 225 tok/s

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

Available at 31 providers28 with public prices · 1 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Kenari
gemini-2-5-flash
GatewayFree1,048,57665,536
QiHangGateway$0.09
tiered >200K: $0.09
$0.711,048,57665,536
PoeGateway$0.21$1.80$0.0211,065,53565,535
Jiekou.AIGateway$0.27$2.251,048,57665,535
CortecsGateway$0.299$2.49$0.029$0.0971,048,5761,048,576
OrcaRouterGateway$0.30$2.50$0.031,048,57665,536
NanoGPTGateway$0.30$2.50$0.031,048,75665,536
VertexOfficialFirst-party$0.30$2.50$0.031,048,57665,536
GoogleOfficialFirst-party$0.30$2.50$0.031,048,57665,536
ImpossiblGateway$0.30$2.50$0.031,048,57665,536

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

1QiHang$53.50
2Poe$109.32
3Cortecs$151.95
4OrcaRouter$152.60
5NanoGPT$152.60
6Vertex · Official$152.60

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

Switch to QiHang to save $99.10/mo (65%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark4 items

NameConditionsScoreMetricSource
Aider Polyglot55.1percent correctSource ↗
Artificial Analysis Coding Index22.2indexSource ↗
SciCode39.4percent correctSource ↗
Terminal-Bench Hard13.6success rateSource ↗

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

Reasoning control

budget_tokenseffort = noneeffort = loweffort = mediumeffort = highToggle (on / off)effort = xhigheffort = maxeffort = minimal

7 / 31 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.50$02026-08-052026-08-132026-08-05 · Input list $0.302026-08-06 · Input list $0.302026-08-07 · Input list $0.302026-08-08 · Input list $0.302026-08-09 · Input list $0.302026-08-10 · Input list $0.302026-08-11 · Input list $0.302026-08-12 · Input list $0.302026-08-13 · Input list $0.302026-08-05 · Output list $2.502026-08-06 · Output list $2.502026-08-07 · Output list $2.502026-08-08 · Output list $2.502026-08-09 · Output list $2.502026-08-10 · Output list $2.502026-08-11 · Output list $2.502026-08-12 · Output list $2.502026-08-13 · Output list $2.502026-08-05 · Min blended $0.2452026-08-06 · Min blended $0.2452026-08-07 · Min blended $0.2452026-08-08 · Min blended $0.2452026-08-09 · Min blended $0.2452026-08-10 · Min blended $0.2452026-08-11 · Min blended $0.2452026-08-12 · Min blended $0.2452026-08-13 · Min blended $0.245