# Gemini 3.8 Flash

Gemini 3.8 Flash costs $0.6375 per 1M input tokens and $3.1875 per 1M output tokens on LLM API, with a 1M-token context window.

Model ID: `gemini-3.8-flash` · Google · Text generation · Released September 2, 2026
Updated: 2026-10-13
Canonical: https://llmapi.ai/models/google-gemini-3-8-flash/

- Input: $0.6375 per 1M tokens
- Output: $3.1875 per 1M tokens
- Cache read: $0.0638 per 1M tokens
- Context: 1M tokens
- Max output: 66K tokens

## Pricing

Lowest price among 3 providers, after discounts.

| Price | Amount | Per |
| --- | --- | --- |
| Input | $0.6375 | per 1M tokens |
| Output | $3.1875 | per 1M tokens |
| Cache read | $0.0638 | per 1M tokens |
| Cache write, 5 minutes | $0.0354 | per 1M tokens |
| Web search | $0.0119 | per search |

**Volume pricing.** At higher monthly volume, Gemini 3.8 Flash may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Providers

Prices after each provider’s discount; the lowest in bold.

| Provider | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output |
| --- | --- | --- | --- | --- | --- |
| [Google AI Studio](https://llmapi.ai/providers/google-ai-studio/) | $0.75 | $3.75 | $0.075 | 1M | 64K |
| [Google Vertex AI](https://llmapi.ai/providers/google-vertex/) | $0.75 | $3.75 | $0.075 | 1.05M | 66K |
| [Novita AI](https://llmapi.ai/providers/novita/) (−15%) | **$0.6375** | **$3.1875** | **$0.0638** | 1.05M | 66K |

## Features

- Tools: Yes
- Parallel tool calls: No
- Image input: Yes
- Reasoning: Yes (Levels: low, medium, high · default medium)
- Prompt caching: Yes
- Structured outputs: Yes
- JSON mode: Yes
- Streaming: Yes
- Web search: Yes
- Batch: Yes

## Call Gemini 3.8 Flash

### Chat Completions (`POST /v1/chat/completions`)

Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="gemini-3.8-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Docs: [Chat Completions docs](https://docs.llmapi.ai/api/v1/chat/completions)

## More from Google

- [Gemini 4 Argon](https://llmapi.ai/models/gemini-4-argon/): $2 / $10 per 1M input / output
- [Gemini 3.5 Flash Lite](https://llmapi.ai/models/google-gemini-3-5-flash-lite/): $0.255 / $2.125 per 1M input / output
- [Gemini 3.7 Flash](https://llmapi.ai/models/google-gemini-3-7-flash/): $0.6375 / $3.1875 per 1M input / output

Prices synced 2026-11-05.

Next step: [Get API key](https://app.llmapi.ai/signup)