> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unifically.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini 4 Neon

> Google's Gemini 4 Neon language model. See supported inputs, parameters, pricing, response fields, and API examples.

Gemini 4 Neon is Google's Gemini 4 model for complex coding, analytical reasoning and multi-step agent work, released on November 18, 2026. Google places it between Hydrogen and Carbon: close to Carbon on coding and reasoning, at much higher speed. It accepts text and image input with a 1M-token context window. Thinking depth is set with `reasoning_effort`: `low` (the default) or `high`. Thinking tokens are billed as output tokens. The first token can take 10 to 30 seconds, so stream the response and set client timeouts with headroom.

Try it in the browser: [Gemini 4 Neon API playground](https://unifically.com/models/gemini-4-neon).

## Model

```
google/gemini-4-neon
```

| | |
| - | - |
| **Provider** | Google |
| **Name** | Gemini 4 Neon |

## Supported Endpoints

* [Chat Completions](https://docs.unifically.com/api-reference/v1-chat-completions.md) — `POST /v1/chat/completions`

> [!CAUTION]
>
> **Send LLM requests to `https://direct-api.unifically.com`, not `https://api.unifically.com`.** The main host sits behind Cloudflare, and Cloudflare's proxy timeout cuts most LLM requests short before the model has finished writing. When that happens you receive a truncated reply and are still charged for every token generated up to the cut-off. `direct-api.unifically.com` reaches the same API without the Cloudflare proxy, so long responses complete in full.

## Example

```bash theme={null}
curl -X POST https://direct-api.unifically.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemini-4-neon",
    "reasoning_effort": "high",
    "stream": true,
    "messages": [
      {"role": "user", "content": "Compare these three vendor quotes, flag the hidden costs, and recommend one in a short table."}
    ]
  }'
```

## Reasoning Effort

| Value | When to use it |
| - | - |
| `low` | Default. Writing, summaries, extraction and routine coding |
| `high` | Multi-step agent work, harder coding and analysis. Slower to start and uses more output tokens |

`minimal` is treated as `low`; `medium`, `xhigh` and `max` are treated as `high`.

## Image Input

Send an image in an `image_url` content part alongside your text, either as a direct https link or inline as a base64 data URI.

```bash theme={null}
curl -X POST https://direct-api.unifically.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "google/gemini-4-neon",
    "messages": [
      {"role": "user", "content": [
        {"type": "text", "text": "Read every number in this chart and return them as a JSON table."},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}}
      ]}
    ]
  }'
```

| | |
| - | - |
| **Accepted shape** | `image_url` part with a direct https link or a `data:image/...;base64` URI |
| **Links** | Must point straight at the image file, with no redirect, up to 14 MB. A link that cannot be downloaded returns `400` with the reason |
| **Billing** | Counted as input tokens at the model's input rate. The `usage.prompt_tokens` field shows the total |

> [!NOTE]
>
> **Volume discounts** are available for almost all models. Reach out at [contact@unifically.com](mailto:contact@unifically.com) to discuss custom pricing.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.