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

# Gemini 4 Carbon

> Gemini 4 Carbon on APIYI: $2 input / $10 output per 1M tokens, 1,048,576 context, 65,536 max output, available in 2 billing groups.

Google's strongest reasoning model, built for long-horizon agentic coding, scientific reasoning and cybersecurity. It has an official 1M unified window and three thinking levels; a 199K-token document passed our test. Google retains per-request model switching, but the latest re-test hit Carbon consistently.

## Specifications

| Item | Value |
| - | - |
| **Model ID** | `gemini-4-carbon` |
| **Vendor** | Google |
| **Vendor release** | 2026-11-10 |
| **Available on APIYI** | 2026-11-11 |
| **Knowledge cutoff** | 2026-03 |
| **Input modalities** | Text, Image, Video, Audio |
| **Output modalities** | Text |
| **Context window** | 1,048,576 tokens |
| **Max output** | 65,536 tokens |
| **Billing** | Usage-based |

## Pricing

Prices in USD per 1M tokens (\$/1M).

| Input | Cached input | Output |
| - | - | - |
| \$2 | \$0.1 | \$10 |

> [!NOTE]
>
> The table shows **list prices**. Recharge promotions and group discounts **stack**; the console reflects the actual charge in real time. See [Pricing](https://docs.apiyi.com/en/pricing.md) and [Recharge promotions](https://docs.apiyi.com/en/faq/recharge-promotions.md).

## Endpoints

| Endpoint | Path | Supported |
| - | - | - |
| `OpenAI Chat Completions` | `POST /v1/chat/completions` | ✅ |
| `OpenAI Responses` | `POST /v1/responses` | — |
| `Anthropic Messages` | `POST /v1/messages` | — |
| `Gemini Generate Content` | `POST /v1beta/models/{model}:generateContent` | ✅ |
| `Image Generations` | `POST /v1/images/generations` | — |
| `Embeddings` | `POST /v1/embeddings` | — |

## Billing groups

| Group | Multiplier | Notes |
| - | - | - |
| `Default` | 1× | List price |
| `SVIP` | 1× | List price |

Some groups carry extra discounts, stackable with recharge bonuses. See [Tokens and groups](https://docs.apiyi.com/en/faq/token-and-groups.md).

## Supported features

| Feature | Supported |
| - | - |
| Streaming | ✅ |
| Tool calling | ✅ |
| Structured outputs | ✅ |
| Vision | ✅ |
| Prompt caching | ✅ |
| Extended thinking | On by default |
| Code execution | ✅ |

## Example request

The example below calls `gemini-4-carbon` through OpenAI Chat Completions (`/v1/chat/completions`). Point base\_url at `https://api.apiyi.com/v1` — everything else matches the official API.

```bash theme={null}
curl https://api.apiyi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $APIYI_API_KEY" \
  -d '{
    "model": "gemini-4-carbon",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

> [!TIP]
>
> Read the key from an environment variable, never hard-coded. In production, issue separate tokens per use case so you can revoke and attribute usage individually.

## Related docs

> [card] [Launch announcement](https://docs.apiyi.com/en/news/gemini-4-carbon-launch.md)
>
> Background, benchmarks and migration notes for Gemini 4 Carbon

> [card] [Gemini 4 Carbon Overview](https://docs.apiyi.com/en/api-capabilities/gemini-4-carbon/overview.md)
>
> Parameters, usage and best practices

> [card] [Native Calls](https://docs.apiyi.com/en/api-capabilities/gemini/native.md)
>
> Parameters, usage and best practices

> [card] [Gemini 4 Argon](https://docs.apiyi.com/en/models/gemini-4-argon.md)
>
> Details for a model in the same family

> [card] [Model pricing directory](https://docs.apiyi.com/en/models.md)
>
> Live pricing, endpoints and groups for all models

> [!NOTE]
>
> Specs on this page are maintained by hand in `models/data/model-details.json`; pricing and endpoints come from the live pricing API and are refreshed with every rebuild.


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