← Back to Hub
Gemini 3.7 Flash
Commercial useGemini 3.7 Flash (Google Vertex) - The LATEST Flash in the Gemini 3.x line (GA 8/13/2026), agentic capability on par with Pro at Flash price/speed, a major leap in code generation + terminal execution. Context 1 million tokens (1,048,576 input / 65,536 output). MULTIMODAL input: text + images (<=3000, 7MB inline/30MB GCS) + audio (<=1 file, ~8.4h) + video (<=10, ~45min with audio/~1h) + pdf/txt documents (<=3000 files). Thinking level LOW/MEDIUM (default)/HIGH - note MINIMAL is NOT supported. Grounding with Google Search/Maps, code execution, function calling, structured output, URL context, computer use (preview). TEXT-only output.
Pricing theo tokenInput 45 credits / 1M (≈ $0.23)Output 225 credits / 1M (≈ $1.13)1M free tokens/mo
24-hour statusNo activity yet
01:00–02:00
No data
02:00–03:00
No data
03:00–04:00
No data
04:00–05:00
No data
05:00–06:00
No data
06:00–07:00
No data
07:00–08:00
No data
08:00–09:00
No data
09:00–10:00
No data
10:00–11:00
No data
11:00–12:00
No data
12:00–13:00
No data
13:00–14:00
No data
14:00–15:00
No data
15:00–16:00
No data
16:00–17:00
No data
17:00–18:00
No data
18:00–19:00
No data
19:00–20:00
No data
20:00–21:00
No data
21:00–22:00
No data
22:00–23:00
No data
23:00–00:00
No data
00:00–01:00
No data
Input
Used to describe the generated output.
Image for reference
Audio for reference
Video for reference
Do sau suy luan. 3.7 Flash chi nhan LOW/MEDIUM/HIGH (mac dinh MEDIUM) - MINIMAL se bao loi. MEDIUM/HIGH tra tom tat suy luan, LOW khong tra.
Priced per token (in 45 · out 225 cr / 1M)
Output
output typetext
Ready to create
Fill the inputs and click Run.
Examples
Click an example to load it into the Playground and try it.
README
Gemini 3.7 Flash API
Gemini 3.7 Flash (Google Vertex) - The LATEST Flash in the Gemini 3.x line (GA 8/13/2026), agentic capability on par with Pro at Flash price/speed, a major leap in code generation + terminal execution. Context 1 million tokens (1,048,576 input / 65,536 output). MULTIMODAL input: text + images (<=3000, 7MB inline/30MB GCS) + audio (<=1 file, ~8.4h) + video (<=10, ~45min with audio/~1h) + pdf/txt documents (<=3000 files). Thinking level LOW/MEDIUM (default)/HIGH - note MINIMAL is NOT supported. Grounding with Google Search/Maps, code execution, function calling, structured output, URL context, computer use (preview). TEXT-only output.
Capabilities
- ✓ chat
How to use it on CinAPI
- 1Create an API key. Go to API Keys to create an ak_… key for your app.
- 2Try it in the Playground. Fill in the Playground tab form and click Run to see instant results (real credits deducted).
- 3Call via the API. POST to /api/v1/calls with a Bearer key to integrate it into your product.
- 4Integrate & scale. One key works for every model (text / image / video). Track usage & logs in the dashboard.
Pricing
Billed by tokens: 45 credits per 1M input tokens (≈ $0.23) and 225 credits per 1M output tokens (≈ $1.13), charged on each call's actual usage. Credits never expire; top up on the Billing page.
Frequently asked questions
Sign up for a CinAPI account, create an API key under API Keys, then call the endpoint with a Bearer key. API-key calls are paid from purchased or bonus credits; your plan's monthly allowance can only be used on the web.
chat