Google AI StudioNot yet certifiedReleased 11/10/2026

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.

View API reference ↓
Input / output priceFrom$2.00 / $10.00per 1M
24h uptime99.98%

Listed for reference. Inference Bureau dispatches only to certified routes, so requests for this model are refused until one is certified. See certified models.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "google/gemini-4-carbon",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Google AI Studio1M1M7.7 s93 tps$2.00$10.00Read $0.100Write —8 featuresNoYesGlobalListed
Google Vertex AI1M1M12.3 s82 tps$2.00$10.00Read $0.100Write —8 featuresYesYesUS EUListed

Uptime

24 hours

Request success rate per provider.

Google AI Studio99.97%
Google Vertex AI99.98%

Throughput

last hour

P50 output tokens per second.

Google AI Studio93 tps
Google Vertex AI82 tps

Latency

last hour

P50 time to first token.

Google AI Studio7.7 s
Google Vertex AI12.3 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "google/gemini-4-carbon",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

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

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. google/gemini-4-carbon. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Gemini 4 Carbon supports up to 1,000,000 output tokens.
reasoning{ effort: 'low' | 'medium' | 'high' }NoReasoning effort, mapped to the provider's native configuration. Reasoning tokens count toward output usage.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 1M-token context window
ImageURL, base64Sent as image_url content parts; counts as input tokens
PDFURL, base64Sent as file content parts; counts as input tokens

More models by Google AI Studio

ModelContextInputOutputCacheRelease
google/gemini-4-hydrogen1M$1.50$7.50Read $0.075Write —11/12/2026
google/gemini-omni-1.2-flash131K$1.50$9.00Read —Write —11/05/2026
google/gemini-4-argon1M$2.00$10.00Read $0.100Write —10/13/2026
google/gemini-nano-banana-2.1131K$1.50$7.50Read $0.15Write —10/06/2026
google/gemini-3.8-flash1M$0.75$3.75Read $0.075Write —09/02/2026
google/gemini-3.7-flash1M$0.75$3.75Read $0.075Write —08/13/2026
google/gemini-3.5-flash-lite1M$0.30$2.50Read $0.030Write —07/21/2026
google/gemini-3.5-flash-lite-batch1M$0.15$1.25Read $0.015Write —07/21/2026
google/gemini-3.6-flash1M$0.75$3.75Read $0.075Write —07/21/2026
google/gemini-3.6-flash-batch1M$0.38$1.88Read $0.038Write —07/21/2026