Google: Gemini 2.5 Flash

google/gemini-2.5-flash

Gemini 2.5 Flash is Google's budget option at $0.3/$2.5 per million input/output tokens, with a 1.05M-token context. It sits mid-board on capability, at #138 of 235 on the TryAii Score — its best showing is #7 on MATH. It's among the fastest models we track, at roughly 75-120 tokens/sec.

Prompt $/1M

$0.300

Completion $/1M

$2.500

Context

1,048,576 tok

Best provider

143 tok/s · Google AI Studio

Specs

Model id: google/gemini-2.5-flash
Display name: Google: Gemini 2.5 Flash
Modality: text+image+file+audio+video->text
Tokenizer: Gemini
Instruct type: —
Context length: 1,048,576
Max completion: 65,535
Prompt $/1M: $0.300
Completion $/1M: $2.500
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Google AI Studiofastest	143	1,041 ms	1,159 ms
Google	52	1,240 ms	1,434 ms
googlefastest	—	—	—
Artificial Analysis	0	0 ms	—

Prompt caching by provider

Provider	Min tokens to cache	Notes
Google AI Studio	2,048 tokens	Gemini 2.5 family (Developer API): implicit caching automatic at 2,048+ tokens with no write premium and no storage — pure upside. Explicit CachedContent adds per-token-hour storage. Implicit lifetime unpublished; don't rely on gaps. (May 2025 sources citing 1,024 are stale.)
Google Vertex	2,048 tokens	Vertex Gemini 2.5: uniform Gemini-2-family 2,048 minimum (implicit AND explicit); 90% discount tier. Explicit CachedContent default TTL 60 min; implicit lifetime unpublished.