How much do Claude Sonnet 4 or Gemini 2.5 Pro cost per month?

For an example workload of 20 million input tokens and 5 million output tokens per month: Claude Sonnet 4: $135. Gemini 2.5 Pro: $75. These are token-only estimates using the displayed rates, without caching discounts, additional tool charges or taxes. Actual bills depend on usage and endpoint pricing.

Which has a larger context window: Claude Sonnet 4 or Gemini 2.5 Pro?

Claude Sonnet 4: 200K tokens of context; maximum output 64K tokens. Gemini 2.5 Pro: 1M tokens of context; maximum output 66K tokens. Context capacity and maximum output are separate limits. A larger context window allows more material in a request but does not guarantee more accurate answers.

Which is better for coding: Claude Sonnet 4 or Gemini 2.5 Pro?

Claude Sonnet 4: Artificial Analysis SciCode not listed. Gemini 2.5 Pro: Artificial Analysis SciCode 46.3%. Compare coding results within the same evaluation, then test representative tasks from your own codebase. A missing score is not a zero, and a single benchmark does not establish the best model for every programming task.

How do Arena Elo, DesignArena, Intelligence Index and MMLU-Pro differ?

These evaluations measure different tasks and use different scales. Arena Elo and DesignArena ratings must remain separate, as must Artificial Analysis Intelligence Index and MMLU-Pro. Compare models within the same evaluation rather than combining scores. Missing results are marked Not listed, not treated as measured zeroes.

Which responds faster: Claude Sonnet 4 or Gemini 2.5 Pro?

Claude Sonnet 4: Artificial Analysis output speed not listed; time to first token not listed. Gemini 2.5 Pro: Artificial Analysis output speed 128 tokens/s; time to first token 18.08 seconds. Output speed measures generation throughput, while time to first token measures the initial wait. Real-world latency also depends on the API provider, request size and load; missing measurements cannot establish a speed winner.

Do Claude Sonnet 4 or Gemini 2.5 Pro support images, audio or video?

Claude Sonnet 4: listed input formats: image, text, file; output formats: text. Gemini 2.5 Pro: listed input formats: text, image, file, audio, video; output formats: text. Input and output support are different capabilities: accepting an image does not mean a model generates images. Confirm formats and file limits for the endpoint you plan to use.

Do Claude Sonnet 4 or Gemini 2.5 Pro support tool calling and structured outputs?

Claude Sonnet 4: listed features: Function calling, Reasoning, Prompt caching. Gemini 2.5 Pro: listed features: Function calling, Structured outputs, JSON mode, Reasoning, Deterministic seed, Prompt caching. Only recorded capabilities are shown; an unlisted feature is not proof that it is unsupported. Availability can vary by API provider, so confirm tool calling and JSON schema support for your chosen endpoint.

Can prompt caching reduce the cost of Claude Sonnet 4 or Gemini 2.5 Pro?

Claude Sonnet 4: cached input price $0.30 per million tokens. Gemini 2.5 Pro: cached input price $0.13 per million tokens. Caching may reduce charges for eligible repeated input when supported by the endpoint. A listed cached rate does not guarantee every request qualifies; cache duration, minimum token counts and any write charges depend on the provider.

Are Claude Sonnet 4 or Gemini 2.5 Pro available through an API?

Claude Sonnet 4: catalog status active; API identifier claude-sonnet-4; listed API hosts Amazon Bedrock, Amazon Bedrock. Gemini 2.5 Pro: catalog status active; API identifier gemini-2.5-pro; listed API hosts Google, Google, Google AI Studio, Google, Google AI Studio, Google, Google AI Studio. Catalog status is not a live availability check. Before integrating, verify the provider's documentation, endpoint access, rate limits, regional availability and data-handling terms.

Models, measured side by side

Claude Sonnet 4 vs Gemini 2.5 Pro

Compare Claude Sonnet 4, Gemini 2.5 Pro by token pricing, context length, benchmark results, speed and tool support.

Highlight best

Monthly workload

Input· million tokensOutput· million tokens

Monthly cost breakdown

InputOutput

Claude Sonnet 4

$135 / mo

Gemini 2.5 Pro

$75 / mo

Performance comparison

Claude Sonnet 4

16.6

Gemini 2.5 Pro

16.1

Overview

Overview	Claude Sonnet 4	Gemini 2.5 Pro
Provider	Anthropic	Google
Released	2025-05	2025-03
Status	Active	Active
Input formats	imagetextfile	textimagefileaudiovideo
Output formats	text	text

Provider

Claude Sonnet 4: Anthropic
Gemini 2.5 Pro: Google

Released

Claude Sonnet 4: 2025-05
Gemini 2.5 Pro: 2025-03

Status

Claude Sonnet 4: Active
Gemini 2.5 Pro: Active

Input formats

Claude Sonnet 4: imagetextfile
Gemini 2.5 Pro: textimagefileaudiovideo

Output formats

Claude Sonnet 4: text
Gemini 2.5 Pro: text

Pricing & capacity

Pricing & capacity	Claude Sonnet 4	Gemini 2.5 Pro
Input / 1M tokens	$3.00	$1.25
Output / 1M tokens	$15	$10
Cached input / 1M	$0.30	$0.13
Monthly cost	$135	$75
Context window	200K	1M
Maximum output	64K	66K

Input / 1M tokens

Claude Sonnet 4: $3.00
Gemini 2.5 Pro: $1.25

Output / 1M tokens

Claude Sonnet 4: $15
Gemini 2.5 Pro: $10

Cached input / 1M

Claude Sonnet 4: $0.30
Gemini 2.5 Pro: $0.13

Monthly cost

Claude Sonnet 4: $135
Gemini 2.5 Pro: $75

Context window

Claude Sonnet 4: 200K
Gemini 2.5 Pro: 1M

Maximum output

Claude Sonnet 4: 64K
Gemini 2.5 Pro: 66K

Benchmarks & performance

Benchmarks & performance	Claude Sonnet 4	Gemini 2.5 Pro
Arena Elo	1,250	1,255
MMLU-Pro	81.9%	82.8%
Intelligence Index	16.6	16.1
GPQA	68.3%	84.4%
Humanity’s Last Exam	4.3%	22.5%
SciCode	Not listed	46.3%
Output speed	Not listed	128 tokens/s
Time to first token	Not listed	18.08 s
DesignArena rating	1,145	1,156
DesignArena win rate	53.4%	57.5%

Arena Elo

Claude Sonnet 4: 1,250
Gemini 2.5 Pro: 1,255

MMLU-Pro

Claude Sonnet 4: 81.9%
Gemini 2.5 Pro: 82.8%

Intelligence Index

Claude Sonnet 4: 16.6
Gemini 2.5 Pro: 16.1

GPQA

Claude Sonnet 4: 68.3%
Gemini 2.5 Pro: 84.4%

Humanity’s Last Exam

Claude Sonnet 4: 4.3%
Gemini 2.5 Pro: 22.5%

SciCode

Claude Sonnet 4: Not listed
Gemini 2.5 Pro: 46.3%

6 of 10

Tools & features

Tools & features	Claude Sonnet 4	Gemini 2.5 Pro
Function calling	Supported	Supported
Structured outputs	Not listed	Supported
JSON mode	Not listed	Supported
Reasoning	Supported	Supported
Built-in web search	Not listed	Not listed
Log probabilities	Not listed	Not listed
Deterministic seed	Not listed	Supported
Parallel tool calls	Not listed	Not listed
Prompt caching	Supported	Supported

Function calling

Claude Sonnet 4: Supported
Gemini 2.5 Pro: Supported

Structured outputs

Claude Sonnet 4: Not listed
Gemini 2.5 Pro: Supported

JSON mode

Claude Sonnet 4: Not listed
Gemini 2.5 Pro: Supported

Reasoning

Claude Sonnet 4: Supported
Gemini 2.5 Pro: Supported

Built-in web search

Claude Sonnet 4: Not listed
Gemini 2.5 Pro: Not listed

Log probabilities

Claude Sonnet 4: Not listed
Gemini 2.5 Pro: Not listed

6 of 9

API & availability

API & availability	Claude Sonnet 4	Gemini 2.5 Pro
API identifier	`claude-sonnet-4`	`gemini-2.5-pro`
API providers	Amazon Bedrock, Amazon Bedrock	Google, Google, Google AI Studio, Google, Google AI Studio, Google, Google AI Studio
Knowledge cutoff	2025-01-31	2025-01-31
Prices checked	Oct 8, 2026	Oct 8, 2026

API identifier

Claude Sonnet 4: claude-sonnet-4
Gemini 2.5 Pro: gemini-2.5-pro

API providers

Claude Sonnet 4: Amazon Bedrock, Amazon Bedrock
Gemini 2.5 Pro: Google, Google, Google AI Studio, Google, Google AI Studio, Google, Google AI Studio

Knowledge cutoff

Claude Sonnet 4: 2025-01-31
Gemini 2.5 Pro: 2025-01-31

Prices checked

Claude Sonnet 4: Oct 8, 2026
Gemini 2.5 Pro: Oct 8, 2026

About the models

Claude Sonnet 4

Hybrid reasoning Claude model with strong agentic coding.

Full pricing & details

Gemini 2.5 Pro

Google's thinking model with 1M-token context.

Full pricing & details

Comparison FAQ

Claude Sonnet 4: $3.00 input and $15 output per million tokens. Gemini 2.5 Pro: $1.25 input and $10 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.

Popular model comparisons

Claude Sonnet 4 vs GPT-4.1 DeepSeek V3 vs Gemini 2.5 Flash DeepSeek V3 vs GPT-4o mini DeepSeek R1 vs Gemini 2.5 Pro Mistral Large vs GPT-4o Gemini 2.5 Pro vs Claude Sonnet 4 Gemini 2.5 Pro vs GPT-4.1 Gemini 2.5 Flash vs GPT-4o mini

Monthly workload

Monthly cost breakdown

Performance comparison

Overview

Pricing & capacity

Benchmarks & performance

Tools & features

API & availability

About the models

Claude Sonnet 4

Gemini 2.5 Pro

Comparison FAQ

Which costs less: Claude Sonnet 4 or Gemini 2.5 Pro?

How much do Claude Sonnet 4 or Gemini 2.5 Pro cost per month?

Which has a larger context window: Claude Sonnet 4 or Gemini 2.5 Pro?

Which is better for coding: Claude Sonnet 4 or Gemini 2.5 Pro?

How do Arena Elo, DesignArena, Intelligence Index and MMLU-Pro differ?

Which responds faster: Claude Sonnet 4 or Gemini 2.5 Pro?

Do Claude Sonnet 4 or Gemini 2.5 Pro support images, audio or video?

Do Claude Sonnet 4 or Gemini 2.5 Pro support tool calling and structured outputs?

Can prompt caching reduce the cost of Claude Sonnet 4 or Gemini 2.5 Pro?

Are Claude Sonnet 4 or Gemini 2.5 Pro available through an API?

Popular model comparisons