gemini-2.5-proGoogle
- endpoints
- 13
- regions
- 11
- api
- chat
- released
- June 2025
- eu routing
- available
capabilities 7/8
The same weights cost 2.0x more on google llc (gemini api) than on google llc (gemini api). That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Google LLC (Gemini API) | Global | 1.0M | $0.63 | $5.00 | $0.13 | zdr |
| 2 | Google LLC (Gemini API) | Global | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 3 |  Google LLC (Vertex AI) | Global | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 4 | Google LLC (Vertex AI) | europe-central2 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 5 | Google LLC (Vertex AI) | europe-north1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 6 | Google LLC (Vertex AI) | europe-west1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 7 | Google LLC (Vertex AI) | europe-west4 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 8 | Google LLC (Vertex AI) | europe-west8 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 9 | Google LLC (Vertex AI) | us-central1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 10 | Google LLC (Vertex AI) | us-east1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 11 | Google LLC (Vertex AI) | us-east5 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 12 | Google LLC (Vertex AI) | us-south1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
| 13 | Google LLC (Vertex AI) | us-west1 | 1.0M | $1.25 | $10.00 | $0.31 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| Math Index | 87.7 | |
| AIME 2025 | 87.7 | |
| MMLU Pro | 86.2 | |
| GPQA Diamond | 84.4 | |
| LiveCodeBench | 80.1 | |
| τ²-Bench | 54.1 | |
| SciCode | 46.3 | |
| Coding Index | 33.3 | |
| Terminal-Bench Hard | 26.5 | |
| Humanity's Last Exam | 22.5 | |
| Intelligence Index | 16.7 | |
| 11 evals | mean | 56.9 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-06-05.
gemini-2.5-pro@eusame routing, restricted to eu-hosted providers. use this id when data residency is a requirement; requests never leave the eu
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="google/gemini-2.5-pro:flex", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.
questions 5
Which providers serve gemini-2.5-pro?
How much does gemini-2.5-pro cost?
Is gemini-2.5-pro open weights?
What is the context window of gemini-2.5-pro?
How do I use gemini-2.5-pro with the OpenAI SDK?
more from google 6
| model | context | from /M | providers |
|---|---|---|---|
| gemini-3.8-flash | 1.0M | $0.75 | 1 |
| gemini-3.7-flash | 1.0M | $0.75 | 1 |
| gemini-3.6-flash | 1.0M | $0.38 | 2 |
| gemini-3.5-flash-lite | 1.0M | $0.15 | 2 |
| gemini-3.1-flash-image | 131K | $0.25 | 2 |
| gemini-3-pro-image | 1.0M | $1.00 | 2 |
route gemini-2.5-pro through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology