Gemini 2.5 Flash API
GOOGLE · Chat, Vision · 1M context
from $0.225 / 1M input tokens -25% vs OpenRouter
Gemini 2.5 FlashはGoogle製の100万トークン超長コンテキストと多モーダル機能・思考機能を備えたモデル。TokenSailではGemini 2.5 Flashを$0.225/1M入力トークンで提供し、公式価格$0.30より25%お得です。長文書や複雑な多モーダル入力の大量処理に最適です。
Pricing Comparison
| Provider | Input / 1M tokens | Output / 1M tokens | Savings |
|---|---|---|---|
| TokenSail | $0.225 | $1.875 | — |
| OpenRouter | $0.30 | $2.50 | -25% |
| Official | $0.30 | $2.50 | -25% |
Quick Start
from openai import OpenAI
client = OpenAI(
base_url="https://api.tokensail.ai/v1",
api_key="YOUR_TOKENSAIL_API_KEY"
)
response = client.chat.completions.create(
model="gemini-2.5-flash",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Specifications
- Provider: GOOGLE
- Context Window: 1M
- Capabilities: Chat, Vision
- API Endpoint: POST https://api.tokensail.ai/v1/chat/completions
- Model ID: gemini-2.5-flash