Model prices / Google / Gemini 2.5 Flash
Gemini 2.5 Flash
Google · released 2025-06-17
The official API price of Gemini 2.5 Flash is $0.3 per 1M input tokens and $2.5 per 1M output tokens (as of 2026-11-12). Context window: 1.05M tokens, up to 65.5K output tokens per request. 32 providers sell it. The lowest is QiHang: $0.09 input, $0.71 output.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| GoogleOfficialgemini-2.5-flash | $0.3 | $2.5 | $0.03 | Official | Official docs |
QQiHangLowestTiered pricinggemini-2.5-flash | $0.09 | $0.71 | — | LowestTiered pricing | Official docs |
JJiekou.AIgemini-2.5-flash | $0.285 | $2.375 | $0.0285 | Official docs | |
CCortecsgemini-2.5-flash | $0.299 | $2.491 | $0.029 | Official docs | |
 AIHubMixgemini-2.5-flash | $0.3 | $2.499 | $0.03 | Official docs | |
3302.AIgemini-2.5-flash | $0.3 | $2.5 | — | Official docs | |
3302.AIgemini-2.5-flash-nothink | $0.3 | $2.5 | — | Official docs | |
AAbacusgemini-2.5-flash | $0.3 | $2.5 | $0.03 | Official docs | |
AAurikogemini-2.5-flash | $0.3 | $2.5 | $0.03 | Official docs | |
 Cloudflare AI Gatewaygoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
CCrossModelgemini/ | $0.3 | $2.5 | $0.03 | Official docs | |
FFastRoutergoogle/ | $0.3 | $2.5 | $0.03 | Official docs |
21 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
FFrogBotgemini-2.5-flash | $0.3 | $2.5 | $0.075 | Official docs | |
HHeliconegemini-2.5-flash | $0.3 | $2.5 | $0.075 | Official docs | |
IImpossiblgoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
MMerge Gatewaygoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
MModelisgemini-2.5-flash | $0.3 | $2.5 | — | Official docs | |
NNanoGPTgemini-2.5-flash | $0.3 | $2.5 | $0.03 | Official docs | |
NNEAR AI Cloudgoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
OOfoxgoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
OOrcaRoutergoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
RRequestygemini-2.5-flash@ | $0.3 | $2.5 | $0.075 | Official docs | |
SStandard Computegoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
 Vercel AI Gatewaygoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
 ZenMuxgoogle/ | $0.3 | $2.5 | $0.03 | Official docs | |
KKilo GatewayDeprecatedgoogle/ | $0.15 | $1.25 | $0.015 | Deprecated | Official docs |
 PoeDeprecatedgoogle/ | $0.21 | $1.8 | $0.021 | Deprecated | Official docs |
DDatabricksDeprecateddatabricks-gemini-2-5-flash | $0.3 | $2.5 | $0.03 | Deprecated | Official docs |
 OpenRouterDeprecatedgoogle/ | $0.3 | $2.5 | $0.03 | Deprecated | Official docs |
SSAP AI CoreDeprecatedgemini-2.5-flash | $0.3 | $2.5 | $0.03 | Deprecated | Official docs |
AAnyAPIgoogle/ | — | — | — | Official docs | |
KKenariDeprecatedgemini-2-5-flash | — | — | — | Deprecated | Official docs |
QQiniuDeprecatedgemini-2.5-flash | — | — | — | Deprecated | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Fast Gemini workhorse for multimodal apps where latency and price matter
Description from models.dev.
Specs
- Type
- Text
- Context
- 1.05M
- Max output
- 65.5K
- Input
- Text, Image, Audio, Video, PDF
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-01
- Open weights
- No
- Released
- 2025-06-17
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.