Google: Gemini 3.7 Flash
gemini-3.7-flash- Input / Output-50%
- $0.75 / $3.75$0.375 / $1.88
- Context
- 1M
- Released
- Aug 13, 2026
- Max output
- 64K
- Modalities
- VisionChat
- Capabilities
- Tool usePrompt Cache
About Gemini 3.7 Flash
Gemini 3.7 Flash is a stable Flash-tier model from Google, released in August 2026, that Google describes as built for complex coding, agentic workflows, and reliable multi-step execution. It reads text and images, supports thinking, calls tools, returns schema-bound JSON, and caches context. It is a step above 3.6 Flash and one step below 3.8 Flash.
Where it works well
- Reasoning can run before the answer, which helps on coding and multi-step tasks.
- Reliable multi-step execution is the stated design goal, useful when an agent must not lose its place.
- Tool calling and schema-bound JSON make results easy to feed into other systems.
- Image input handles screenshots, diagrams, and scanned documents.
When to choose another model
- Gemini 3.8 Flash is the newer model that Google presents as its most capable Flash tier.
- Thinking adds latency, so simple lookups are better served by Flash-Lite.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Text to textGemini APIPOST/v1beta/models/gemini-3.7-flash:generateContentAPI format:curl "https://api.tokenlab.sh/v1beta/models/gemini-3.7-flash:generateContent" \ -H "Content-Type: application/json" \ -H "x-goog-api-key: sk-xxx" \ -d '{ "contents": [ {"role": "user", "parts": [{"text": "Hello!"}]} ] }'
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Promotional Standard
per 1M tokens- Official price
- Input $0.75 / Output $3.75 / Cache read $0.075
- Verified price
- Input $0.375 / Output $1.88 / Cache read $0.0375
- Discount
- -50%
Cache read
- Official price
- $0.075
- Verified price
- $0.0375
- Discount
- -50%
Charged per call, only when the model uses the tool.
Web search
- Official price
- $0.014/search
- Verified price
- $0.007/search
- Discount
- -50%
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Promotional Standard | Input $0.75 / Output $3.75 / Cache read $0.075 | Input $0.375 / Output $1.88 / Cache read $0.0375 | -50% |
| Prompt cache pricing | |||
| Cache read | $0.075 | $0.0375 | -50% |
| Tool feesCharged per call, only when the model uses the tool. | |||
| Web search | $0.014/search | $0.007/search | -50% |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
- 30-day success rate
- 99.8%
- 7-day median latency
- 13.2 sn=271
- 7-day P95 latency
- 53 sn=271
- 30-day requests
- 1K+
- Last active
- 1 hour ago
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Gemini 3.7 Flash in Console with a prompt ready to edit or send.
Help me try gemini-3.7-flash with a short message at /v1beta/models/gemini-3.7-flash:generateContent. Show the reply, latency, and cost.
Use cases
Best for- Vision
Feature implementation
Have an agent read a ticket, edit several files, and run tests.
Workflow automation
Chain approvals, lookups, and notifications where each step depends on the last.
Code review
Read a diff, flag risky changes, and explain each finding so that a human reviewer can decide quickly what to accept.
Data cleanup
Reason through inconsistent records and propose normalization rules before applying them, so the cleanup can be audited first.
Prompt examples
Read this ticket and the linked files, implement the change, and list which tests you ran.
Review this diff for concurrency bugs and rank the findings by severity.
These two customer records look like duplicates. Explain which fields conflict and what rule would merge them safely.
This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.
FAQ
What is Gemini 3.7 Flash designed for?
Complex coding, agent workflows, and multi-step execution that has to stay reliable from first step to last. It is a thinking-capable Flash model with tool and image support.
Does it support thinking?
Yes. It can reason before replying, which improves results on code and planning. Leave that effort low for short interactive turns to keep responses quick.
How does it differ from 3.6 Flash?
3.7 Flash is the later model and adds reasoning, with a stronger emphasis on dependable multi-step runs. 3.6 Flash is framed around coding loops and visual reasoning without thinking.
Is 3.8 Flash a better choice?
Often, for long-horizon software engineering. 3.7 Flash remains a sound choice when you have already tuned prompts for it and its results meet your bar.
How much does Gemini 3.7 Flash cost?
On TokenLab, Gemini 3.7 Flash costs Input $0.375 / Output $1.88 per 1M tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the context window and output limit of Gemini 3.7 Flash?
Gemini 3.7 Flash accepts up to 1,048,576 tokens of context and returns up to 65,536 tokens in one response.
Which endpoint should Gemini 3.7 Flash use?
Use https://api.tokenlab.sh/v1beta/models/gemini-3.7-flash:generateContent for Gemini 3.7 Flash. The request example below shows the matching code shape.
Which operations does Gemini 3.7 Flash support?
Gemini 3.7 Flash supports Text to text. Select an operation above to see its endpoint and request example.
Compare Gemini 3.7 Flash
Sources
Reviewed Oct 2, 2026
More from Google