GoogleReleased on May 1, 2024

Gemini 1.5 Pro: API Pricing, Context Window & Benchmarks

Gemini 1.5 Pro is a language model from Google, released in May 2024, with multimodal input.

Gemini 1.5 Pro is a mid-size multimodal model optimized for a wide range of reasoning tasks. It can process large amounts of data at once, including 2 hours of video, 19 hours of audio, codebases with 60,000 lines of code, or 2,000 pages

Input
TextImage
Output
Text
Speed
Latency p95700ms
Throughput P9585.0char/s
Cost
$3.33/ 1M · 8:1 in:out
$2.50 in · $10.0 out

Gemini 1.5 Pro benchmarks

Rankings

Quality Tracker

Gemini 1.5 Pro Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Wed Jul 22 2026
Notice missing or incorrect data?

Gemini 1.5 Pro pricing

Providers

Gemini 1.5 Pro starts at $2.50 per million input tokens and $10.00 per million output tokens via Google.

ProviderInput $/MOutput $/MContext in / outTTFT p50 / p95 sOutput avg / p5 c/sSuccess 7dModalities in / out
Google logoGoogle
$2.50$10.002.1M/8.2K
—/0.70
85/—
—
/

Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests. Success is calculated from completed versus failed requests over the trailing seven days.

Gemini 1.5 Pro context window

Input and output token limits for Gemini 1.5 Pro, plus how it ranks on long-context understanding.

InputOutput
2.1Mtokens
8Ktokens
≈ 3.2k pages of text
2.1M
8K128K1M

Gemini 1.5 Pro API

Available from the model provider

Gemini 1.5 Pro has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

Gemini 1.5 Pro latency

Gemini 1.5 Pro time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Gemini 1.5 Pro examples

Recent arena outputs from Gemini 1.5 Pro, picked from the highest-ranked matchups.

Gemini 1.5 Pro license

Gemini 1.5 Pro is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of November 2023.

License
Proprietary
Hosted access
Knowledge cutoff
November 2023

Proprietary license - usage restrictions apply

Gemini 1.5 Pro resources

Official sources for Gemini 1.5 Pro: api documentation, official playground, paper or system card, official launch post.

Gemini 1.5 Pro vs other models

The most-compared alternatives to Gemini 1.5 Pro are Claude 3.5 Sonnet, Llama 3.3 70B Instruct, MiMo-V2.5-Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like Gemini 1.5 Pro

Models ranked just above and below Gemini 1.5 Pro by LLM Stats score.

 

Claude 3.5 Sonnet

Score pending
DetailsCompare
 

Llama 3.3 70B Instruct

Score pending
DetailsCompare
 

MiMo-V2.5-Pro

Score pending
DetailsCompare
 

Phi 4 Reasoning Plus

Score pending
DetailsCompare
 

Grok-2

Score pending
DetailsCompare
 

Nova Pro

Score pending
DetailsCompare

FAQ

Common questions about Gemini 1.5 Pro.

When was Gemini 1.5 Pro released?

Gemini 1.5 Pro was released on May 1, 2024 by Google. This is the official Gemini 1.5 Pro release date tracked on LLM Stats.

How much does Gemini 1.5 Pro cost?

Gemini 1.5 Pro pricing starts at $2.50 per million input tokens and $10.00 per million output tokens via Google, the lowest price among tracked providers.

Is Gemini 1.5 Pro available via API?

Yes, Gemini 1.5 Pro is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

Who created Gemini 1.5 Pro?

Gemini 1.5 Pro was created by Google.

What is the license for Gemini 1.5 Pro?

Gemini 1.5 Pro is released under the Proprietary license.

What is the knowledge cutoff date for Gemini 1.5 Pro?

Gemini 1.5 Pro has a knowledge cutoff of November 2023, meaning it was trained on data up to that point and may not know about events after it.

Is Gemini 1.5 Pro multimodal?

Yes, Gemini 1.5 Pro is multimodal and can accept both text and images as input.

What is Gemini 1.5 Pro latency?

Gemini 1.5 Pro p95 time to first token is 0.70 seconds via Google over the trailing 7 days. Lower time to first token means the model begins responding sooner for chat, agents and API workloads.

Where can I use Gemini 1.5 Pro?

Gemini 1.5 Pro is available through 1 provider including Google.

Where is the Gemini 1.5 Pro paper or technical report?

Gemini 1.5 Pro has a paper or technical report available at https://arxiv.org/pdf/2403.05530. Use that source for architecture, training, release and evaluation details.

What models should I compare Gemini 1.5 Pro against?

Common Gemini 1.5 Pro comparisons include Gemini 1.5 Pro vs Claude 3.5 Sonnet, Gemini 1.5 Pro vs Llama 3.3 70B Instruct, Gemini 1.5 Pro vs MiMo-V2.5-Pro. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.