Model introduction
gemini-3.6-flash is a Google model available through MoleAPI with openai, gemini access. It fits OpenAI compatible, Gemini compatible, Vision, Prompt cache workflows, with pricing synced from the MoleAPI console.
Model capabilities
Specifications come from the cited model material. Catalog tags help identify access features; use the source documentation for exact limits.
Verified specifications
- Catalog status
- Currently available on MoleAPI
- Compatible protocols
- openai, gemini
- Available billing groups
- Standard, Discount
Sources: MoleAPI console pricing catalog
Model pricing and access
Prices are read directly from the MoleAPI console catalog and shown by current billing group and context tier.
Your final charge follows the account group shown in the console.
Live pricing source
Pricing table
USD / 1M tokensStandardx1defaultInput $1.5 · Output $7.5
Input
$1.5 / 1M tokens
Output
$7.5 / 1M tokens
Cache read
$0.15 / 1M tokens
Discountx0.8discountInput $1.2 · Output $6
Input
$1.2 / 1M tokens
Output
$6 / 1M tokens
Cache read
$0.12 / 1M tokens
Access protocols
Available billing groups: Standard, Discount
- openai
- POST
- /v1/chat/completions
- gemini
- POST
- /v1beta/models/{model}:generateContent
Complete model guide
Prepared from vendor sources and independently reviewed. · 2026-07-28
Model Positioning and Core Capabilities
Gemini 3.6 Flash is the primary model in Google's Flash series, designed for large-scale AI agents with a focus on coding, knowledge work, and multimodal tasks. Google positions it as a production model that balances efficiency, latency, and reliability, and states that it can complete multi-step workflows with fewer reasoning steps and tool calls.[5]
The model was released on July 21, 2026, as an efficiency-focused successor to Gemini 3.5 Flash.[5]
Capabilities and Specifications
Gemini 3.6 Flash's public positioning emphasizes efficiency in multi-step task execution, as well as performance in coding, knowledge work, and multimodal tasks.[5]
| Item | Publicly available information |
|---|---|
| Release date | July 21, 2026.[5] |
| Model positioning | A primary Flash series model for large-scale AI agents.[5] |
| Focus tasks | Coding, knowledge work, multimodal tasks, and multi-step workflows.[5] |
| Efficiency characteristics | Google states that it can reduce the reasoning steps and tool calls needed to complete multi-step workflows.[5] |
Use Cases
Gemini 3.6 Flash is designed for agent applications that combine reasoning, tool calls, and multimodal information processing. It also supports coding assistance, knowledge work processing, and multimodal analysis tasks.[5]
Google's published comparison results show that the model achieves higher results than Gemini 3.5 Flash on tests including DeepSWE, MLE Bench, OSWorld-Verified, and GDPval-AA v2; these results reflect model performance in vendor-published evaluations.[5]
Important Limitations
Gemini 3.6 Flash includes enhanced safety protections against CBRN risks and cyberattack misuse.[5]
Gemini API usage limits are typically managed by requests per minute, input tokens per minute, and requests per day; exceeding the limit in any dimension triggers restrictions. Actual quotas are calculated per project and vary by model, usage tier, and account status.[12]
Sources
[5] Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber [12] Rate limits | Gemini API - Google AI for Developers
Code examples
These examples use MoleAPI's OpenAI-compatible endpoint and run after you replace the API key.
curl https://api.moleapi.com/v1/chat/completions \
-H "Authorization: Bearer $MOLEAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.6-flash",
"messages": [{"role": "user", "content": "Hello"}]
}'Frequently asked questions
How is gemini-3.6-flash priced?
This page reads prices from the MoleAPI console API and updates with model prices, context tiers, and account groups.
How can I access gemini-3.6-flash?
Protocols and endpoints come from the supported_endpoint_types field in the MoleAPI model catalog.
How do I switch an existing project to gemini-3.6-flash?
Keep the MoleAPI API address and key, replace the model parameter with the model ID on this page, then check protocol-specific parameter differences.
Where do the gemini-3.6-flash model details come from?
Only availability, billing, and protocol facts from the MoleAPI catalog are currently verified, so unconfirmed model specifications are not added.