Google/gemini-4-carbon/Released Nov 2026

Gemini 4 Carbon

Deep reasoning for math, science, and code

AgentText

About Gemini 4 Carbon

gemini-4-carbon is a Multimodal LLM. It is Google's Gemini 4 reasoning model for complex software engineering, mathematical and scientific problem solving, factual accuracy, and autonomous multi-step agents. Google highlights gains in formal proofs, experimental data analysis, and vulnerability discovery.

Some other noteworthy features of gemini-4-carbon include configurable thinking levels (low, medium, and high, with medium as the default), structured output, function calling, code execution, search grounding, URL context, file search, and computer use. It accepts text, images, audio, video, and PDFs and outputs text. It suits long, hard problems where accuracy matters more than latency, and its sibling Gemini 4 Argon trades some depth for faster, cheaper turns.

MetricValue
Context Length1M tokens
Max Output64K tokens
MultilingualYes

Ready to build with Gemini 4 Carbon?

Try Gemini 4 Carbon in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/chat/completions \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "gemini-4-carbon",
  "messages": [
    {
      "role": "user",
      "content": "Try sending a message."
    }
  ]
}'

API endpoint

See the API reference for request and response formats.

POSThttps://hub.oxen.ai/api/ai/chat/completions