Skip to content

Model detail

Gemini 4 Carbon

Provided by Google
Delisted Pay-as-you-go

Gemini 4 Carbon is a reasoning model for sustained software engineering, scientific problem solving and multimodal knowledge work.

Model specs

Model ID
gemini-4-carbon
Context length
1.048576M
Max output
1.048576M
I/O modalities
Released
2026-11

02

API endpoints

One MixRoute gateway, OpenAI-compatible

  • Gemini /v1beta/models/{model}:generateContent POST
  • OpenAI-compatible /v1/chat/completions POST

03

Pricing

Flat rate, unit: /1M Tokens

Pricing updated

Input

$2.0000 /1M Tokens

Completion

$10.0000 /1M Tokens

Cache read

$0.1000 /1M Tokens

05

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Coding

Gemini 4 Carbon is built for writing and reviewing code, and it reads images alongside text. It accepts input such as text, image and video, and returns text. Its capabilities are broken down in the section just below. Run it on one file from your own repository and check the patch before you commit.

What should you check before using it?

1,048,576 context, 1,048,576 output tokens

Gemini 4 Carbon accepts up to 1,048,576 tokens of context and returns up to 1,048,576 output tokens per request. Check that your longest prompt and its expected answer fit inside both limits before you size production traffic.

Why use it through MixRoute?

One MixRoute key reaches Gemini 4 Carbon

One MixRoute key covers gemini-4-carbon, on the same account as the rest of the catalog. MixRoute supports calling Gemini 4 Carbon through its OpenAI-compatible endpoint; point your client at https://api.mixroute.ai/v1 with the model ID gemini-4-carbon and re-run your integration tests.

07

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Available:

Tool calling

Gemini 4 Carbon supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.
Available:

Structured output

Gemini 4 Carbon can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.
Available:

Streaming

Gemini 4 Carbon supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.
Available:

Prompt caching

Gemini 4 Carbon supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.
Available:

Vision input

Gemini 4 Carbon can process image inputs alongside text.

EX Pass a base64-encoded image in a image_url content part alongside text messages.

08

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Share of the same prefix read repeatedly, up to 100%

09

FAQ

Reasoning tokens are billed as output on Gemini 4 Carbon, at $10 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.

One endpoint, a testable decision

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.