Gemini 3.5 Flash Lite
gemini-3.5-flash-lite
These are Mengbi Router customer prices in USD per 1M tokens. Provider: Google; Context: 2M; Input price: $0.124; Output price: $1.04.
- Low latency
- Cost effective
AI models and pricing
Model specs
- Provider
- Context
- 2M
- Max output
- 64K
- Released
- Jun 2026
- Input modalities
- Text, Image, PDF
- Output modalities
- Text
- Tool calling
- Supported
- Structured output
- Supported
- Currency
- USD
- Model ID
- gemini-3.5-flash-lite
Model pricing and access details
USD / 1M tokens| Model | Official | Mengbi | Discount |
|---|---|---|---|
| Input price | $0.30 | $0.124 | 58% OFF |
| Output price | $2.5 | $1.04 | 58% OFF |
| Cache read price | $0.03 | $0.0124 | 58% OFF |
Estimated cost for common usage
Estimates based on current Mengbi Router prices, so you can plan real request costs.
| Token volume | Input | Output | Input + output total |
|---|---|---|---|
| 10K tokens | $0.00124 | $0.0104 | $0.0116 |
| 100K tokens | $0.0124 | $0.104 | $0.116 |
| 1M tokens | $0.124 | $1.04 | $1.16 |
| 10M tokens | $1.24 | $10.36 | $11.6 |
Estimates use the current prices above and exclude cache-hit discounts. Your invoice is metered by the actual token usage of each request.
API protocol compatibility
Keep your SDK. Change one line.
Use the protocol your stack already speaks.
const client = new OpenAI({
apiKey: process.env.MENGBI_ROUTER_KEY,
baseURL: process.env.MENGBI_ROUTER_BASE_URL,
})
const response = await client.chat.completions.create({
model: 'gemini-3.5-flash-lite',
messages,
})Frequently asked questions
Common questions about the Gemini 3.5 Flash Lite API: pricing, capabilities, and integration.
How much does the Gemini 3.5 Flash Lite API cost?
Through Mengbi Router, Gemini 3.5 Flash Lite costs $0.124 per 1M input tokens and $1.04 per 1M output tokens. Cached input is billed at $0.0124 per 1M tokens.
What is the context window of Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite supports a 2M-token context window. A single request can generate up to about 64K output tokens.
Does Gemini 3.5 Flash Lite support tool calling and structured output?
Yes. Gemini 3.5 Flash Lite supports the tools parameter in chat.completions for function calling. It also supports response_format with a JSON Schema for structured output.
What input and output formats does Gemini 3.5 Flash Lite support?
It accepts Text, Image, and PDF and returns Text.
How do I call Gemini 3.5 Flash Lite with the OpenAI SDK?
Keep your OpenAI SDK, point the base URL at Mengbi Router, use your Mengbi API key, and set model to gemini-3.5-flash-lite in the request.
Which company provides Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite is provided by Google and available through Mengbi Router with one API key and pay-as-you-go billing. The model was first released in Jun 2026.