Gemini 3.7 Flash

Gemini 3.7 Flash is a generally available Gemini model for coding, agentic workflows, web development, and multimodal reasoning. AnyFast exposes it through the native Gemini generateContent API with the stable model ID gemini-3.7-flash.

Key capabilities

1M token context - Up to 1,048,576 input tokens and 65,536 output tokens
Multimodal input - Text, image, video, audio, and PDF input; text output
Coding and agents - Improved software engineering, issue resolution, multi-step execution, and fewer failed agent loops
Web development - Improved design adherence when generating interfaces from design references or auditing implementations against them
Tools - Function calling, code execution, File Search, Google Search, Google Maps, URL context, structured output, and Computer Use (Preview)
Thinking levels - low, medium, and high; the default is medium
Caching and batch processing - Supports context caching, Batch API, Flex inference, and Priority inference upstream

Model specifications

Property	Value
Model ID	`gemini-3.7-flash`
Release stage	Generally available (GA)
Inputs	Text, image, video, audio, and PDF
Output	Text
Input token limit	1,048,576
Output token limit	65,536
Default thinking level	`medium`

Quick example

curl "https://www.anyfast.ai/v1beta/models/gemini-3.7-flash:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{ "text": "Review this retry design and identify possible race conditions." }]
      }
    ],
    "generationConfig": {
      "thinkingConfig": {
        "thinkingLevel": "medium"
      },
      "maxOutputTokens": 2048
    }
  }'

import requests

response = requests.post(
    "https://www.anyfast.ai/v1beta/models/gemini-3.7-flash:generateContent",
    params={"key": "YOUR_API_KEY"},
    json={
        "contents": [{
            "role": "user",
            "parts": [{"text": "Review this retry design and identify possible race conditions."}],
        }],
        "generationConfig": {
            "thinkingConfig": {"thinkingLevel": "medium"},
            "maxOutputTokens": 2048,
        },
    },
)
response.raise_for_status()
print(response.json()["candidates"][0]["content"]["parts"][0]["text"])

Thinking levels

Choose a thinking level based on latency and task difficulty:

Level	Recommended use
`low`	Latency-sensitive chat, drafting, incident response, and quick analysis
`medium`	Default; coding and agentic tasks that need balanced latency and reasoning
`high`	Difficult coding, mathematics, tool use, and complex reasoning

minimal is not supported by Gemini 3.7 Flash and returns an error.

Conversation requirements

Requests must not end with a non-empty model role turn. End the conversation with a non-empty user turn; otherwise the API returns HTTP 400.

Parameters

Parameter	Type	Required	Description
`key`	string	Yes	API key in the query string
`contents`	array	Yes	Conversation turns containing text or multimodal parts
`systemInstruction`	object	No	System instruction with a `parts` array
`generationConfig.thinkingConfig.thinkingLevel`	string	No	`low`, `medium` (default), or `high`
`generationConfig.maxOutputTokens`	integer	No	Maximum output tokens, up to 65,536
`generationConfig.responseMimeType`	string	No	Output MIME type, such as `application/json`
`generationConfig.responseSchema`	object	No	JSON schema used with structured output
`tools`	array	No	Function declarations and supported built-in Gemini tools

API Reference

View the interactive API reference for Gemini 3.7 Flash.

Getting started

Model Introduction

Resources

Gemini 3.7 Flash

Key capabilities

Model specifications

Quick example

Thinking levels

Conversation requirements

Parameters

API Reference

Official references

​Key capabilities

​Model specifications

​Quick example

​Thinking levels

​Conversation requirements

​Parameters

API Reference

​Official references

Key capabilities

Model specifications

Quick example

Thinking levels

Conversation requirements

Parameters

Official references