Last refreshed 2026-06-29. Next refresh: weekly.
Why use Gemini 3 Pro Preview on Vercel AI Gateway?
Vercel AI Gateway offers Gemini 3 Pro Preview with pay-as-you-go pricing at $2.00/1M 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 3 Pro Preview across 2 providers to find the best fit for your use caseInput / 1M
$2.00
Output / 1M
$12.00
Cache
read $0.20
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-3-pro-previewRequest 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-3-pro-preview",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "google/gemini-3-pro-preview", not the LLMReference slug "gemini-3-pro-preview".
- 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 3 Pro Preview Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| GCP Vertex AI | $2.00 | $12.00 |
| Vercel AI Gateway | $2.00 | $12.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $2.00 |
| Output tokens | $12.00 |
| Query | $14.00 |
Capabilities
VisionMultimodalJSON / Tool useStructured Outputs
About Gemini 3 Pro Preview
Deprecated/shut down March 9, 2026. Vertex: $0.20/$12.00 (<=200K), $0.40/$18.00 (>200K). Migrate to Gemini 3.1 Pro.
Get Started
Model Specs
Released2025-09-01
Context1m
ArchitectureDecoder Only