GOOGLE MODEL GUIDE
Gemini 3.7 Flash API
Google's production-ready Flash model for coding, multimodal reasoning, agent workflows, and high-volume applications.
Image, PDF, audio and video understanding, search grounding, structured extraction, and multi-step agents.
Native audio or image generation, Live API workloads, or fixed long-term budgets that ignore the promo-price change.
Choosing and integrating
Gemini 3.7 Flash API pricing breakdown
Gemini 3.7 Flash (gemini-3.7-flash) is billed by token usage. Prices below are USD per 1M tokens. LLMFly AI rates already include the 0.4x group multiplier; do not apply it again. Provider reference prices are separate. These rates come from the site's Model Plaza snapshot; confirm live catalog and account rates before calling.
Example: a request with 10,000 uncached input tokens and 1,000 output tokens costs approximately $0.0045 in LLMFly AI token charges. This excludes cache writes, tools, retries, and other additional fees.
- Platform and provider prices use their own input-token tiers. Do not apply provider long-context multipliers to platform prices.
- Not listed does not mean free. Account for cache reads, cache writes, and uncached input in their respective billing categories.
- Token cost = tokens in each billing category × its price per million ÷ 1,000,000. Add tools and other charges separately.
| Price source | Input tokens per request | Input | Output | Cache write | Cache read | 1h cache write |
|---|---|---|---|---|---|---|
| LLMFly AI | Single rate | $0.3 | $1.5 | Not listed | $0.03 | Not listed |
| Provider reference | Single rate | $0.75 | $3.75 | Not listed | $0.075 | Not listed |
Start with the input-modality decision
| Input | Support | Typical work |
|---|---|---|
| Text / code | Supported | Coding, extraction, structured outputs |
| Images / PDFs | Supported | Documents, screenshots, chart understanding |
| Audio / video | Supported | Media analysis and cross-modal reasoning |
| Audio / image generation | Not supported | Use a dedicated generation model |
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.
| Level | Test first for | Watch |
|---|---|---|
| low | Classification, extraction, simple transforms | Latency and schema pass rate |
| medium | Default production baseline | Quality-cost balance |
| high | Complex coding, multi-step agents | Incremental passes and tool turns |
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.
Budget for the end of introductory pricing
| Period | Input / 1M | Output / 1M |
|---|---|---|
| Through 2026-12-31 | $0.75 | $3.75 |
| Published post-promo rate | $1.50 | $7.50 |
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.
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
}'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.
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.
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.