Last refreshed 2026-06-29. Next refresh: weekly.
Why use Gemini 2.5 Pro on Vercel AI Gateway?
Vercel AI Gateway offers Gemini 2.5 Pro with pay-as-you-go pricing at $1.25/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Gemini 2.5 Pro across 4 providers to find the best fit for your use caseInput / 1M
$1.25
Output / 1M
$10.00
Cache
read $0.125
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
google/gemini-2.5-proRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="google/gemini-2.5-pro",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "google/gemini-2.5-pro", not the LLMReference slug "gemini-2.5-pro".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Gemini 2.5 Pro Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Google AI Studio | $1.25 | $10.00 |
| GCP Vertex AI | $1.25 | $10.00 |
| OpenRouter | $1.25 | $10.00 |
| Vercel AI Gateway | $1.25 | $10.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $1.25 |
| Output tokens | $10.00 |
| Query | $35.00 |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsCode ExecutionPrompt CachingBatch API
About Gemini 2.5 Pro
Google DeepMind's most capable Gemini 2.5 model with native thinking/reasoning support. Features a 1M-token context window, multimodal inputs (text, image, audio, video), function calling, and strong performance across coding, mathematics, and scientific reasoning tasks.
Get Started
Model Specs
Released2025-06-17
Context1m
ArchitectureDecoder Only
Knowledge cutoff2025-01