Gemini 3.7 Flash
by Google
Google hybrid reasoning model combining fast multimodal inference with controllable thinking capabilities, a 1M context window, and up to 64K output tokens.
Run queries immediately, pay only for usage
Per 1M Tokens
About this model
Gemini 3.7 Flash is Google's hybrid reasoning model, seamlessly combining rapid response with deep, controllable thinking. It features a 1M-token context window, advanced multimodal capabilities (text, code, image), and high agentic performance. Available through the DOS.AI gateway with unified billing and OpenAI compatibility.
Capabilities
Use Cases
- Complex reasoning & math
- Agentic coding
- Multimodal analysis
- High-volume production workloads
Model Details
- Provider
- Model ID
- gemini-3.7-flash
- Parameters
- Flash (Hybrid)
- Context Length
- 1M tokens
- Category
- chat
API Usage
Use the DOS API to integrate Gemini 3.7 Flash into your applications. Our API is compatible with OpenAI's client libraries for easy migration.
Model ID
gemini-3.7-flashPython
from dos import DOS
client = DOS()
response = client.chat.completions.create(
model="gemini-3.7-flash",
messages=[
{"role": "user", "content": "Hello, how are you?"}
]
)
print(response.choices[0].message.content)cURL
curl https://api.dos.ai/v1/chat/completions \
-H "Authorization: Bearer $DOS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.7-flash",
"messages": [
{"role": "user", "content": "Hello, how are you?"}
]
}'Node.js
import DOS from 'dos-ai';
const client = new DOS();
const response = await client.chat.completions.create({
model: "gemini-3.7-flash",
messages: [
{ role: "user", content: "Hello, how are you?" }
]
});
console.log(response.choices[0].message.content);Related Models
DOS.AI Auto
Smart routing - automatically picks the best model for your request. Free for simple tasks, paid models for complex ones.
DOS.AI
DOS.AI's hosted Qwen 3.5 35B-A3B model for text generation.
Gemma 3 1B IT
Google Gemma 3 1B on-device text model providing low-latency execution for mobile and edge computing.