Model

Gemini 2.5 Pro

Recorded as suitable for chat, rag, reasoning, multilingual, vision.

Model card

Source: Model registry API
Verified: 19 Sep 2026
Confidence: High

01What this is

Author: google
Family: Gemini
Task: text-generation
Hugging Face: not listed
OpenRouter: google/gemini-2.5-pro
Also known as: Gemini 2.5 Pro, gemini-2.5-pro, gemini 2.5

02Registry facts

19 Sep 2026

LicenceFACT: not returned by the registry; Evidence not verified
ParametersFACT: not returned by the registry; Evidence not verified
Context lengthFACT: not returned by the registry; Evidence not verified
Downloads (30 days)FACT: not returned by the registry; Evidence not verified
LikesFACT: not returned by the registry; Evidence not verified
GatedFACT: no; FreshRetrieved 19 Sep 2026

Model

hosted context length · Google AI StudioFACT: 1048576; Verification may be outdatedRetrieved 19 Sep 2026
hosted context length · GoogleFACT: 1048576; Verification may be outdatedRetrieved 19 Sep 2026

Pricing

hosted price completion per m · Google AI StudioFACT: 5.0000; AgeingRetrieved 19 Sep 2026
hosted price completion per m · GoogleFACT: 18.0000; AgeingRetrieved 19 Sep 2026
hosted price prompt per m · Google AI StudioFACT: 0.6250; AgeingRetrieved 19 Sep 2026
hosted price prompt per m · GoogleFACT: 2.2500; AgeingRetrieved 19 Sep 2026

Other

available on platform · vendorFACT: vendor; AgeingRetrieved 19 Sep 2026

03VRAM by quantisation

ASSESSMENT

Peak VRAM for serving this model, computed by lib/deployment/hardware.ts from weights + KV cache + 15% runtime overhead. Inputs: — parameters, 8,192 tokens of context (assumed — none fetched yet), 4 concurrent requests (assumed).

Decimal GB (10⁹ bytes), matching how GPU memory is advertised.
Quantisation	Weights	KV cache	Overhead	Total
fp16Needs a fetched parameter count.	not yet fetched
int8Needs a fetched parameter count.	not yet fetched
int4Needs a fetched parameter count.	not yet fetched

No parameter count has been fetched for this model, so there is nothing to compute. We will not infer a size from the model’s name.

04Hardware profiles

No hardware profile was sized for this answer.

05Hosted providers

Prompt (per million tokens, USD)FACT

0.625

Source: openrouter

FreshRetrieved 19 Sep 2026

Completion (per million tokens, USD)FACT

FreshRetrieved 19 Sep 2026

Provider	Quantisation	Context
Google	unknown	1,048,576
Google	unknown	1,048,576
Google AI Studio	unknown	1,048,576
Google	unknown	1,048,576
Google AI Studio	unknown	1,048,576
Google	unknown	1,048,576

06Deployment stacks

1 using it

Private cloudAssistant on Google Vertex AIA model on Vertex AI (Model Garden or the managed-API option), Vertex AI Search for retrieval over your content, a web application you build, Google Cloud identity for sign-in, and private connectivity so the call stays inside your project.

07Evidence

7 verified

01
Tier 2official vendor legal documentationVendor legal and technical documentation
Models
https://ai.google.dev/gemini-api/docs/models
AgeingRetrieved 19 Sep 2026sha256:a417d81386c4
1 record
02–07
Tier 4official repository / model cardOpenRouter
OpenRouter endpoints — google/gemini-2.5-pro
https://openrouter.ai/api/v1/models/google/gemini-2.5-pro/endpoints
Verification may be outdatedRetrieved 19 Sep 2026sha256:b45aeaf7aed0
6 records · · · · ·

Improve this page

From the field

0 deployments · 0 questions

Nobody has reported deploying this here yet, and no question has been opened against this page. Both appear once a reviewer accepts them.