Google

Gemini 4 Carbon API Pricing 2026

Compare pricing, benchmarks, and providers for Gemini 4 Carbon. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Gemini 4 Carbon was released on November 10, 2026. Pricing starts at $1.00 per million input tokens and $5.00 per million output tokens. The model supports a context window of up to 1.0M tokens. API access is available through Google.

Context Window
1.0M
tokens
Pricing
Input$1.00
Output$5.00
Cached$0.050
per 1M tokens
Speed
Output89 tok/s
TTFT72.99s
median latency
Capabilities
VisionAudio InToolsCaching

Gemini 4 Carbon is priced at $1.00 per million input tokens and $5.00 per million output tokens. It has a context window of 1,048,576 tokens. It is available from 3 providers, with Google AI Studio the cheapest at $1.00 per million input tokens (input prices range from $1.00 to $2.00). It runs at roughly 89 tokens per second with a 72.99s time to first token. On benchmarks, Gemini 4 Carbon scores Intelligence 60.0 (99th percentile). Over the past ~90 days its cheapest input price has fallen 54.5%, from $2.20 to $1.00 per million tokens.

Pricing Comparison

Compare Gemini 4 Carbon with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$1.000
$5.000
—
—
—
1,048,576
Try
$1.000
$4.050
—
—
87.2
1,048,576
Try
$1.000
$3.000
—
—
—
-
Try
$1.000
$2.000
—
—
—
-
Try
$1.000
$2.000
—
—
—
256,000
Try
$1.000
$6.000
—
—
—
1,048,576
Try
$1.000
$3.000
—
—
—
256,000
Try
$1.000
$5.000
—
—
—
200,000
Try
$1.000
$3.000
—
—
—
131,072
Try
$1.000
$10.000
—
—
—
1,048,576
Try
$1.000
$5.000
—
—
—
1,050,000
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Gemini 4 Carbon is available from multiple providers with different pricing and availability.

3
Providers
$1.000
Cheapest Input/M
$5.000
Cheapest Output/M
Google AI Studio
Best Price

Provider Pricing

3 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
Google AI Studio
Google AI Studio
Best Price
$1.000
$5.000
$0.050
$0.094
100.0%
$2.000
$10.000
$0.100
$0.188
100.0%
$2.000
$10.000
$0.100
$0.188
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Gemini 4 Carbon perform? Vote based on your experience.

Cost vs. Quality

Compare Gemini 4 Carbon's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Detailed Benchmark Scores

Intelligence
60.0 (99th pct)
Coding
-
Math
-
MMLU Pro
-
GPQA
-
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Gemini 4 Carbon

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Gemini 4 Carbon directly in your browser.

Open Playground

Frequently Asked Questions

Gemini 4 Carbon costs $0.001000 per 1,000 input tokens and $0.005000 per 1,000 output tokens.
Gemini 4 Carbon is available from 3 providers. Google AI Studio offers the best price.
Google AI Studio offers Gemini 4 Carbon at $1.00 per million input tokens, the lowest of 3 providers (input prices range from $1.00 to $2.00 per million tokens).
Gemini 4 Carbon scores Intelligence 60.0 (99th percentile). Only benchmarks with published data for this model are shown.
Yes. Over the past ~90 days, the cheapest input price for Gemini 4 Carbon has dropped 54.5%, from $2.20 to $1.00 per million tokens.
We compare Gemini 4 Carbon with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Google Models

See pricing for all Google models.

View all Google models →