This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Google has launched a newer release, Gemini 3 Pro Preview. We suggest considering it instead.
Gemini 2.5 Pro API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Gemini 2.5 Pro for your use-case.
Fastest
Google (AI Studio)Google VertexOutput speed
Total 2 providers
Lowest Latency
Google (AI Studio)Google VertexTime to first answer token
Total 2 providers
Lowest Price
Google VertexGoogle (AI Studio)Blended price (per 1M tokens)
Total 2 providers
Gemini 2.5 Pro is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Google (AI Studio) (135.5 t/s) and Google Vertex (110.9 t/s).
- For latency, Google (AI Studio) (19.04s) and Google Vertex (28.53s) offer the lowest time to first answer token.
- For pricing, Google Vertex (1.34) and Google (AI Studio) (1.34) offer the lowest blended prices per 1M tokens.
- Google (AI Studio) offers the best performance with both the highest speed and lowest latency. For cost optimization, Google Vertex provides the most competitive pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Gemini 2.5 Pro
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Gemini 2.5 Pro providers
Gemini 2.5 Pro is available through 2 API providers: Google Vertex and Google (AI Studio). Each provider offers different performance characteristics and pricing.
Gemini 2.5 Pro is currently available through 2 API providers that we benchmark and track.
The fastest providers for Gemini 2.5 Pro by output speed are Google (AI Studio) (135.5 t/s) and Google Vertex (110.9 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for Gemini 2.5 Pro are Google (AI Studio) (19.04s) and Google Vertex (28.53s). Lower latency means faster initial response time.
The most affordable providers for Gemini 2.5 Pro by blended price are Google Vertex ($1.34 per 1M tokens) and Google (AI Studio) ($1.34 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Gemini 2.5 Pro are Google Vertex ($1.25 per 1M input tokens) and Google (AI Studio) ($1.25 per 1M input tokens).
The providers with the lowest output token pricing for Gemini 2.5 Pro are Google Vertex ($10.00 per 1M output tokens) and Google (AI Studio) ($10.00 per 1M output tokens).
All 2 providers of Gemini 2.5 Pro support JSON mode for structured output.
All 2 providers of Gemini 2.5 Pro support function calling (tool use).
For Gemini 2.5 Pro, Google (AI Studio) offers the best performance with highest speed and lowest latency. For cost optimization, Google Vertex provides the most competitive pricing.
When choosing a provider for Gemini 2.5 Pro, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Gemini 2.5 Pro's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview