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.

Parameters
Flash (Hybrid)
Context Length
1M
Category
chat
Available Serverless

Run queries immediately, pay only for usage

$0.79in|$3.94out

Per 1M tokens

Try this modelView documentation

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

Hybrid reasoningVisionLong context (1M)Tool callingCode generationStreaming

Use Cases

  • Complex reasoning & math
  • Agentic coding
  • Multimodal analysis
  • High-volume production workloads

Providers

One model, several sources. DOS routes to the first that answers and falls back automatically, or you can pin a provider per request.

ProviderInput /1MOutput /1MContext
GoogleAvailable
$0.79$3.941M

Observed performance

Provider results over the last 7d.

Updated Sep 14, 10:02 AM UTC
Google
36 samples
Uptime
100.0%
P50 response
1.26 s
P95 response
1.73 s

Uptime is based on observed valid provider attempts. Not an SLA.

Latency is measured to provider response headers, not end-to-end completion.

Model Details

Provider
Google
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-flash

Python

python
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

bash
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

javascript
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);