Claude Opus 5.5 vs Gemini 4 Carbon

Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.

Try Claude Opus 5.5 in Chat

At a glance

Generated from the rows below

Choose Claude Opus 5.5 for

The longest output: 128,000 tokens
Included in 30 subscription plans
The most routes on Phaseo: 4

Choose Gemini 4 Carbon for

The lowest cost per typical request ($0.009)
The largest context window: 1,048,576 tokens
The only one that takes audio, video

The models are statistically tied on the Epoch Capabilities Index: their 95% confidence intervals overlap.

Overview

Lab

Anthropic

Google

Context window

1Mtokens

1.05Mtokensfrom provider listings

Max output

128Ktokens

65.5Ktokensfrom provider listings

Takes

Returns

Routes on Phaseo

4 providers

2 providers

Released

22 Sept 2026

10 Nov 2026

Pricing

Prices on the route and tier chosen under each model

Priced onAnthropic · StandardGoogle AI Studio · Standard

Input

$4.00/ 1M tokensRegion: US$4.40

$2.00/ 1M tokens

Output

$20.00/ 1M tokensRegion: US$22.00

$10.00/ 1M tokens

Cache read

$0.20/ 1M tokensRegion: US$0.22

$0.10/ 1M tokens

Cache write, 5 minutes

$5.00/ 1M tokensRegion: US$5.50

No write fee listed

Cache write, 1 hour

$8.00/ 1M tokensRegion: US$8.80

No write fee listed

Typical request2K tokens in, 500 out

$0.018

$0.009

What will it cost?

Estimate a month of requests on the route and tier chosen for each model

Input tokens per request

Output tokens per request

Cached share of input (%)

Requests per day

ModelMonthly costPer requestPer month

Claude Opus 5.5Anthropic · Standard$0.018$540.00

Gemini 4 CarbonGoogle AI Studio · Standard$0.009$270.00

Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.

Performance

Live gateway traffic

Latency p50last 5 days

No traffic in the last 5 days

17.5 s

Throughput p50last 5 days

No traffic in the last 5 days

15.3 tps

Requests, last 24 hours

None in the last 24 hours

Activity

Tokens sent through Phaseo each day over the last 30 days

Tokens, last 30 days

3.27K

24.7K

Per day

3.27K

16 Oct14 Nov

24.7K

16 Oct14 Nov

Input

21.8K

Output

3.19K

1.66K

Reasoning

1.2K

Requests

Features

Features from the parameters Phaseo routes support

Tool calling

Yes

Structured outputs

Yes

Reasoning effort

Yes

Web search

Not listed

Prompt cachingon the chosen route

Yes

Quantisationon the chosen route

Not stated

Benchmarks

Only results that two or more of the selected models report get a row

Compare at effort

Epoch Capabilities Index Independent

Higher is better · dot is the estimate, band is the 95% confidence interval · Epoch AI, CC BY 4.0

Claude Opus 5.5168.5

Gemini 4 Carbon169.8

Every interval overlaps, so these models are statistically tied on this index.

Artificial Analysis Intelligence Index Independent

Higher is better · at High effort · 2 of 2 models tested

Claude Opus 5.551.8

Gemini 4 Carbon60

Where they rank

The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.

Artificial Analysis Intelligence Index62 models ranked

Epoch Capabilities Index165 models ranked

Cost

Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better

$2,716

$5,333

General

Artificial Analysis Progress Index v1matched by effort level

344.0

350.8

Agents

Agents' Last Examreported by the lab

63.2%Agents' Last Exam v1

77.4%

Science

Terminal-Bench Science 0.1reported by the lab

63.3%Terminal-Bench-Science 0.1

64.8%

Lab-reported results come from each lab’s own launch materials and may use different settings, so none is marked best. Independent results come from third-party evaluators.

Providers

Where each model runs on Phaseo, with standard-tier prices per 1M tokens. Providers that serve more of these models come first.

Anthropic

$4.00 in · $20.00 out1M context · Standard, Batch, Priority

—

Google AI Studio

—

$2.00 in · $10.00 out1.05M context · Standard, Batch, Flex, Priority

Azure

$4.00 in · $20.00 out1M context

—

Google Vertex

—

$2.00 in · $10.00 out1.05M context · Standard, Batch, Flex, Priority

Inference.net

$4.00 in · $20.00 out1M context

—

Anthropic (US)

$4.40 in · $22.00 out1M context · Standard, Batch, Priority

—

Also listed, not routed

9 providers

—

To price the whole page on one of these providers, pick it under the model’s name at the top.

Details

Knowledge cutoff

Not published

Status

Available

Licence

Proprietary

Subscription plans

30 plansClaude Enterprise, Claude Max, Claude Pro…

25 plansCursor Enterprise, Cursor Pro, Cursor Pro+…

API docs

Not published

Claude Opus 5.5 vs Gemini 4 Carbon: side-by-side summary

Claude Opus 5.5 and Gemini 4 Carbon are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.

Claude Opus 5.5 is from Anthropic. It has a 1,000,000-token context window. On its cheapest route it costs $4.00 per 1M input tokens and $20.00 per 1M output tokens.

Gemini 4 Carbon is from Google. It has a 1,048,576-token context window. On its cheapest route it costs $2.00 per 1M input tokens and $10.00 per 1M output tokens.

Claude Opus 5.5 model details, providers and pricing Gemini 4 Carbon model details, providers and pricing

Claude Opus 5.5 vs Gemini 4 Carbon at a glance

Claude Opus 5.5 and Gemini 4 Carbon compared on price, context window and benchmark score
Attribute	Claude Opus 5.5	Gemini 4 Carbon
Lab	Anthropic	Google
Input price per 1M tokens	$4.00	$2.00
Output price per 1M tokens	$20.00	$10.00
Context window	1,000,000 tokens	1,048,576 tokens
Max output	128,000 tokens	65,536 tokens
Artificial Analysis Intelligence Index	59.1 (#3)	60.0 (#2)

Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.

Frequently asked questions

Which is cheaper, Claude Opus 5.5 or Gemini 4 Carbon?

Gemini 4 Carbon is cheaper for both input and output tokens. Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens; Gemini 4 Carbon costs $2.00 and $10.00, each on its cheapest standard route on Phaseo.

Which has the longer context window, Claude Opus 5.5 or Gemini 4 Carbon?

Gemini 4 Carbon has the longer context window at 1,048,576 tokens, compared with 1,000,000 tokens for Claude Opus 5.5.

Which scores higher on the Artificial Analysis Intelligence Index, Claude Opus 5.5 or Gemini 4 Carbon?

Gemini 4 Carbon scores higher on the Artificial Analysis Intelligence Index. Gemini 4 Carbon scores 60.0, ranked #2 of 62. Claude Opus 5.5 scores 59.1, ranked #3 of 62.

Can I use Claude Opus 5.5 and Gemini 4 Carbon through one API?

Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.