GOOGLE MODEL GUIDE

Gemini 3.7 Flash API

Google's production-ready Flash model for coding, multimodal reasoning, agent workflows, and high-volume applications.

Core specificationsSpecifications reviewed September 1, 2026
Official model IDgemini-3.7-flash
Context / max output1,048,576 / 65,536
Vendor input / output per 1M$0.75 input / $3.75 output through Dec 31, 2026
Reasoninglow · medium · high
Selection verdictGemini 3.7 Flash stands out for the combination of multimodal input, tools, and throughput.
Best fit

Image, PDF, audio and video understanding, search grounding, structured extraction, and multi-step agents.

Avoid when

Native audio or image generation, Live API workloads, or fixed long-term budgets that ignore the promo-price change.

02

Read by decision

01
Multimodal matrix

Start with the input-modality decision

InputSupportTypical work
Text / codeSupportedCoding, extraction, structured outputs
Images / PDFsSupportedDocuments, screenshots, chart understanding
Audio / videoSupportedMedia analysis and cross-modal reasoning
Audio / image generationNot supportedUse a dedicated generation model
02
Reasoning levels

Choose low, medium, or high thinking

Medium is the documented default. Compare quality, latency, output tokens, and tool retries on the same tasks before raising effort.

LevelTest first forWatch
lowClassification, extraction, simple transformsLatency and schema pass rate
mediumDefault production baselineQuality-cost balance
highComplex coding, multi-step agentsIncremental passes and tool turns
03
Tool capability

Combine grounding and built-in tools deliberately

  • Search grounding for current web facts.
  • Maps grounding for location and map context.
  • URL context for processing specified web pages.
  • Code execution for verifiable calculations and code tasks.
  • File search and function calling for private knowledge and business actions.
04
Price timeline

Budget for the end of introductory pricing

PeriodInput / 1MOutput / 1M
Through 2026-12-31$0.75$3.75
Published post-promo rate$1.50$7.50
05
Integration

Call Gemini 3.7 Flash through LLMFly AI

The sample covers text only. Use the model ID and endpoint shown in Model Plaza when testing media input, web-search grounding, and tools.

request.exampleCopy-ready
curl https://app.llmfly.ai/v1/chat/completions \
  -H "Authorization: Bearer $LLMFLY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.7-flash",
    "messages": [{"role": "user", "content": "Summarize the tradeoffs in three bullets."}],
    "stream": false
  }'
06
Migration

Migration checklist from older Gemini models

  • Remove deprecated sampling parameters.
  • Revalidate the default thinking level and quality.
  • Test file size, preprocessing, and errors for each modality.
  • Separate preview tools from stable capabilities and add safety controls for computer use.
  • Include post-promotion pricing in budgets and alerts.
07
Constraints

Explicit Gemini 3.7 Flash boundaries

  • The introductory vendor price expires on December 31, 2026 and is scheduled to increase afterward.
  • Computer use remains a preview capability and requires separate safety controls.
  • The model does not provide audio or image generation and does not support the Live API.
  • Remove deprecated sampling parameters when migrating from older Gemini versions.
08
Source boundary

Gemini 3.7 Flash specification sources and usage notes

Specifications, tools, and introductory pricing were checked against Google Gemini 3.7 Flash documentation: https://ai.google.dev/gemini-api/docs/models/gemini-3.7-flash. Confirm which capabilities the current LLMFly AI route exposes in Model Plaza.

Frequently asked questions

Which inputs does Gemini 3.7 Flash support?

It accepts text, images, video, audio, and PDFs and produces text output.

Which thinking level should I use?

Start with the documented medium default, test low for simpler work, and evaluate high for complex coding and multi-step agents.

When does the introductory price end?

Google's documentation lists the current introductory pricing through December 31, 2026, with a higher published rate afterward.

Does it generate images or audio?

No. This model focuses on multimodal understanding with text output.

Does every LLMFly AI route expose all grounding tools?

Not necessarily. Vendor capability and gateway route support differ, so verify Model Plaza and a real request.

Test Gemini 3.7 Flash with your own task

Create an API key, confirm the model ID, and start with a small representative request.

Get API Key