Gemini 4 Carbon

by November 10, 20261M context64K output

Gemini 4 Carbon is Google's most capable Gemini model, built for the hardest tasks in software engineering, enterprise knowledge work, and scientific and mathematical reasoning. It spends more tokens than Gemini 4 Argon to explore problems, reason deeply, and verify its own work, and it accepts text, images, video, audio, and PDFs with a 1M-token context window, up to 65,536 output tokens, and configurable thinking effort. It is well suited to multi-package code migrations, document synthesis for legal and financial analysis, research problems, and agent workflows that run extended build-and-verify loops.

Gemini 4 Carbon is served through Runware's compatible endpoints, which take another provider's request format. Point the SDK you already use at Runware by changing the base URL and the API key, and set model to google:gemini@4-carbon.

Requests and responses keep the provider's format, so its reference documents every parameter.

Endpoint	Format
`/v1/chat/completions`	OpenAI Chat Completions

Chat Completions

cURL

curl -X POST https://api.runware.ai/v1/chat/completions \
  -H "Authorization: Bearer $RUNWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google:gemini@4-carbon",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="your_runware_api_key",
    base_url="https://api.runware.ai/v1",
)

response = client.chat.completions.create(
    model="google:gemini@4-carbon",
    messages=[{"role": "user", "content": "What is the capital of France?"}],
)

print(response.choices[0].message.content)

TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'your_runware_api_key',
  baseURL: 'https://api.runware.ai/v1',
});

const response = await client.chat.completions.create({
  model: 'google:gemini@4-carbon',
  messages: [{ role: 'user', content: 'What is the capital of France?' }],
});

console.log(response.choices[0].message.content);

Vercel AI SDK

import { createOpenAICompatible } from '@ai-sdk/openai-compatible';
import { generateText } from 'ai';

const runware = createOpenAICompatible({
  name: 'runware',
  apiKey: 'your_runware_api_key',
  baseURL: 'https://api.runware.ai/v1',
});

const { text } = await generateText({
  model: runware('google:gemini@4-carbon'),
  prompt: 'What is the capital of France?',
});

console.log(text);

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="google:gemini@4-carbon",
    api_key="your_runware_api_key",
    base_url="https://api.runware.ai/v1",
)

response = llm.invoke("What is the capital of France?")

print(response.text)

Compatible APIs covers streaming, tool calling and how the endpoint differs from OpenAI, and the OpenAI API reference lists every parameter.