---
id: "google/gemini-4-carbon"
also: ["google/gemini-4-carbon-20261110", "requesty/google/gemini-4-carbon", "vercel/google/gemini-4-carbon"]
cheapest_list_usd_per_m: "1.0 in, 5.0 out, at google-ai-studio/flex on openrouter"
cheapest_effective_usd_per_m: "0.4475 in, 10.0 out, at vertex on requesty"
context: 1048576
max_output: 943718
input: ["audio", "file", "image", "text", "video"]
output: ["text"]
released: "2026-11-10"
reasoning: ["high", "medium", "low"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p"]
endpoints: 12
gateways: "openrouter (7), requesty (3), vercel (2)"
no_training: 11
trains: 0
retains_prompts: 3
intelligence: 60
---
# Google: Gemini 4 Carbon

Gemini 4 Carbon is Google’s reasoning model for complex software engineering, sustained agentic workflows, and cybersecurity defense. It combines a 1M-token context window with multimodal understanding, tool calling, and structured outputs for working across large codebases and documents. Carbon emphasizes reliable execution of multi-step plans, clearer handling of uncertainty, and identifying, validating, and remediating security vulnerabilities.