# Gemini 4 Carbon MCP and API - Chat model by Google | FlyMy.AI

> Google Gemini 4 Carbon is Google's strongest reasoning model for complex coding, analysis and agents, with image, audio, video and PDF input.

Page: https://flymy.ai/mcp/models/gemini-4-carbon/

MCP / Models / Language models

# Gemini 4 Carbon MCP: complex reasoning with no API key

Google Gemini 4 Carbon is Google's strongest reasoning model for complex coding, analysis and agents, with image, audio, video and PDF input. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Gemini 4 Carbon](https://flymy.ai/mcp/models/gemini-4-carbon/#start) [Inputs and price](https://flymy.ai/mcp/models/gemini-4-carbon/#inputs)

No API key, $2.00 / $10.00 per 1M tokens, Chat model, Google, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Gemini 4 Carbon in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/gemini-4-carbon.md. Help me connect the FlyMy.AI MCP to this assistant, then run Gemini 4 Carbon (flymyai/gemini-4-carbon) for this task: Ask Gemini 4 Carbon: review this function for bugs and explain the fix.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/gemini-4-carbon.md)

## What Gemini 4 Carbon does

It always thinks. Send a prompt, or a chat history in messages with images as image_url parts, and get a text answer from a 1M-token context. reasoning_effort is low, medium or high (medium by default) and max_tokens caps one request at 32,768 tokens (65,536 when streamed); system_prompt works as usual, and private_mode keeps the prompt and answer out of FlyMy.AI storage. Your FlyMy.AI key also works on the OpenAI-compatible Chat Completions endpoint and on Google's generateContent API at the model's FlyMy.AI address, so the official Google GenAI SDK runs once you change its base URL; that route also takes audio, video and PDF. Billing follows the tokens Google reports, at Google's own price. Tools Google runs itself, such as Search grounding, are not offered.

Guide: [LLM API: GPT, Claude and Gemini with One Key](https://flymy.ai/blog/llm-api-gpt-claude-gemini/)

## Gemini 4 Carbon inputs

Every input of `flymyai/gemini-4-carbon` as its live schema lists them. Returns `output` (string), `finish_reason` (string), `stream_details` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-prompt) `prompt` | string required What to ask Gemini 4 Carbon |
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-messages) `messages` | string optional Chat history as a JSON array of {role, content}; used instead of the prompt |
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-system_prompt) `system_prompt` | string optional Instructions for the whole chat |
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-reasoning_effort) `reasoning_effort` | string optional Allowed: high, medium, low Default: `medium` How much effort Gemini 4 Carbon puts into the answer, reasoning included |
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-max_tokens) `max_tokens` | integer optional Allowed: 1 to 32768 Most tokens to generate, reasoning included |
| [#](https://flymy.ai/mcp/models/gemini-4-carbon/#input-private_mode) `private_mode` | boolean optional Default: `false` Keep the prompt and the answer out of FlyMyAI storage and logs (synchronous requests only) |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Ask Gemini 4 Carbon: review this function for bugs and explain the fix.”** runs `flymyai/gemini-4-carbon`

**“Summarize this contract into five bullet points with Gemini 4 Carbon.”** runs `flymyai/gemini-4-carbon`

**“With Gemini 4 Carbon, draft a friendly reply to this customer email.”** runs `flymyai/gemini-4-carbon`

## Gemini 4 Carbon price

$2.00 per 1M input tokens, $10.00 per 1M output tokens, cached input $0.10 per 1M; from 2026-12-01 $4.00 / $20.00 per 1M. Cached input is $0.10 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Gemini 4 Carbon from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/gemini-4-carbon",
  "input": {
    "prompt": "Explain in two sentences what an MCP server is."
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. Text models answer on the streaming route.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/gemini-4-carbon/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'
```

### With the OpenAI SDK

Gemini 4 Carbon also answers the OpenAI Chat Completions protocol.

```
from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/gemini-4-carbon/openai/v1", api_key="YOUR_FLYMYAI_KEY")
reply = client.chat.completions.create(
    model="flymyai/gemini-4-carbon",
    messages=[{"role": "user", "content": "Explain in two sentences what an MCP server is."}],
)
print(reply.choices[0].message.content)
```

## Questions about Gemini 4 Carbon

**Do I need a Google API key for Gemini 4 Carbon?**

No. Gemini 4 Carbon runs on FlyMy.AI's account, so you need no Google key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Gemini 4 Carbon cost?**

$2.00 per 1M input tokens, $10.00 per 1M output tokens, cached input $0.10 per 1M; from 2026-12-01 $4.00 / $20.00 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-12.

**How do I use Gemini 4 Carbon in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Ask Gemini 4 Carbon: review this function for bugs and explain the fix." Your agent reads the inputs with get_model_schema and runs flymyai/gemini-4-carbon with run_model.

**What does Gemini 4 Carbon need as input?**

Gemini 4 Carbon requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

**Can I call Gemini 4 Carbon from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/gemini-4-carbon/predict/stream/ with your FlyMy.AI API key in the X-API-KEY header; it also answers the OpenAI Chat Completions protocol at https://api.flymy.ai/api/v1/flymyai/gemini-4-carbon/openai/v1.

## More language models models

Chat and reasoning models for code, documents and agents, plus typed decisions for routing and triage.

### Gemini 3.5 Flash-Lite

The current low-cost Gemini for high-volume work, with thinking from minimal up.

Chat model / $0.30 / $2.50 per 1M tokens

Link: https://flymy.ai/mcp/models/gemini-3-5-flash-lite/

### Gemini 3.8 Flash

Google's current Flash model, its suggested start for everyday apps and agents.

Chat model / $0.75 / $3.75 per 1M tokens

Link: https://flymy.ai/mcp/models/gemini-3-8-flash/

### Gemini 4 Argon

The efficient Gemini 4: quicker answers and fewer tokens per turn than Carbon.

Chat model / $2.00 / $10.00 per 1M tokens

Link: https://flymy.ai/mcp/models/gemini-4-argon/

### Gemini 3 Flash

The Gemini 3 generation at Flash speed, with thinking you can turn down.

Chat model / $0.50 / $3.00 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-3-flash-preview/

### Gemini 3.1 Flash Lite

The cheapest Gemini text model for extraction, labels and short drafts at scale.

Chat model / $0.25 / $1.50 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-31-flash-lite-preview/

### Gemini 3.1 Pro

Gemini 3.1 Pro for the hard problems: long documents, code and careful reasoning.

Chat model / $2.00 / $12.00 per 1M tokens

Link: https://flymy.ai/mcp/models/google-gemini-31-pro-preview/

## Go to the source

[Gemini 4 Carbon in the playground →](https://app.flymy.ai/models/flymyai/gemini-4-carbon), [Gemini 4 Carbon guide in the docs →](https://docs.flymy.ai/guides/use-llms), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-12: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.