Claude vs Gemini API pricing. Side by side.

Anthropic’s Claude and Google’s Gemini models, matched tier by tier, with each lab’s list price and what the same tokens cost on Zurelay, where both run on one API key.

Claude models
10
Gemini models
6
Below list
46–65%
Get your API keyCompare by tier

By tier

Matched tier by tier. As each lab describes them.

Each lab’s most capable model

Fable is Anthropic’s tier above Opus. Gemini 4 Argon is Google’s frontier model for long, complex work in software engineering, research and security.

Claude Fable 5.1
Anthropic
65%off
Input / 1M
$3.50 $10.00
Output / 1M
$17.50 $50.00
Context
1M tokens
10K requests
$157.50
Reads
Text, images and PDFs
Gemini 4 Argon
Google
60%off
Input / 1M
$0.80 $2.00
Output / 1M
$4.00 $10.00
Context
1M tokens
10K requests
$36.00
Reads
Text, images, PDFs, audio and video

For the typical load: Gemini 4 Argon costs 77% less than Claude Fable 5.1 ($36.00 against $157.50).

Coding and agents at volume

Anthropic calls Sonnet 5.5 its best combination of speed and intelligence. Google calls Gemini 3.8 Flash its most intelligent Flash model, built for long-horizon software engineering and agents.

Claude Sonnet 5.5
Anthropic
55%off
Input / 1M
$0.90 $2.00
Output / 1M
$4.50 $10.00
Context
1M tokens
10K requests
$40.50
Reads
Text, images and PDFs
Gemini 3.8 Flash
Google
58%off
Input / 1M
$0.32 $0.75
Output / 1M
$1.59 $3.75
Context
1M tokens
10K requests
$14.35
Reads
Text, images, PDFs, audio and video

For the typical load: Gemini 3.8 Flash costs 65% less than Claude Sonnet 5.5 ($14.35 against $40.50).

Fast and low-cost

Haiku 5.5 is Anthropic’s fastest and lowest-priced model. Gemini 3.5 Flash-Lite is the fastest, most cost-effective model in Google’s Gemini 3.5 series.

Claude Haiku 5.5
Anthropic
60%off
Input / 1M
$0.04 $0.10
Output / 1M
$0.20 $0.50
Context
1M tokens
10K requests
$1.80
Reads
Text, images and PDFs
Gemini 3.5 Flash-Lite
Google
58%off
Input / 1M
$0.12 $0.30
Output / 1M
$1.04 $2.50
Context
1M tokens
10K requests
$7.60
Reads
Text, images, PDFs, audio and video

For the typical load: Claude Haiku 5.5 costs 76% less than Gemini 3.5 Flash-Lite ($1.80 against $7.60).

The typical load is 10,000 requests of 2,000 tokens in and 500 out. Struck-through prices are each lab’s list price.

Every model

Every Claude and Gemini model. Cheapest first.

Claude and Gemini API prices on Zurelay and at each lab's list price, cheapest first
ModelContextInput / 1MOutput / 1M10K requestsYou save
Claude Haiku 5.5Anthropic · claude-haiku-5-51M
$0.04
$0.10
$0.20
$0.50
$1.80
$4.50
60%off
Gemini 3.1 Flash-LiteGoogle · gemini-3.1-flash-lite1M
$0.10
$0.25
$0.59
$1.50
$4.95
$12.50
61%off
Gemini 3.5 Flash-LiteGoogle · gemini-3.5-flash-lite1M
$0.12
$0.30
$1.04
$2.50
$7.60
$18.50
58%off
Gemini 3.8 FlashGoogle · gemini-3.8-flash1M
$0.32
$0.75
$1.59
$3.75
$14.35
$33.75
58%off
Gemini 3.7 FlashGoogle · gemini-3.7-flash1M
$0.32
$0.75
$1.59
$3.75
$14.35
$33.75
58%off
Claude Haiku 4.5Anthropic · claude-haiku-4-5200K
$0.54
$1.00
$2.70
$5.00
$24.30
$45.00
46%off
Gemini 4 ArgonGoogle · gemini-4-argon1M
$0.80
$2.00
$4.00
$10.00
$36.00
$90.00
60%off
Gemini 3.1 ProGoogle · gemini-3.1-pro1M
$0.80
$2.00
$4.80
$12.00
$40.00
$100.00
60%off
Claude Sonnet 5.5Anthropic · claude-sonnet-5-51M
$0.90
$2.00
$4.50
$10.00
$40.50
$90.00
55%off
Claude Opus 5.5Anthropic · claude-opus-5-51M
$1.40
$4.00
$7.00
$20.00
$63.00
$180.00
65%off
Claude Opus 5Anthropic · claude-opus-51M
$1.75
$5.00
$8.75
$25.00
$78.75
$225.00
65%off
Claude Opus 4.7Anthropic · claude-opus-4-71M
$1.78
$5.00
$8.93
$25.00
$80.25
$225.00
64%off
Claude Opus 4.8Anthropic · claude-opus-4-81M
$2.40
$5.00
$12.00
$25.00
$108.00
$225.00
52%off
Claude Opus 4.6Anthropic · claude-opus-4-61M
$2.40
$5.00
$12.00
$25.00
$108.00
$225.00
52%off
Claude Fable 5.1Anthropic · claude-fable-5-11M
$3.50
$10.00
$17.50
$50.00
$157.50
$450.00
65%off
Claude Fable 5Anthropic · claude-fable-51M
$3.50
$10.00
$17.50
$50.00
$157.50
$450.00
65%off

Prices in US dollars per 1M tokens, live from the catalog, with each lab's list price struck through. 10K requests is 10,000 requests of 2,000 tokens in and 500 out, at each price. You save is on output tokens.

Try both

One key for both. Test on your own work.

Benchmarks don’t tell you which model handles your prompts better. Run the same requests through both and compare the answers, the tokens and the bill.

On Zurelay, every Claude and Gemini model is on the same key and the same OpenAI-compatible endpoint, so switching is a change of model name. Claude also answers on Anthropic’s Messages API, for Claude Code and the Anthropic SDKs.

compare.py
from openai import OpenAI
client = OpenAI(base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY")
prompt = [{"role": "user", "content": "Refactor this function: ..."}]
# Same key, same code: only the model name changes
for model in ["claude-sonnet-5-5", "gemini-3.8-flash"]:
    reply = client.chat.completions.create(model=model, messages=prompt)
    print(model, reply.usage.total_tokens, reply.choices[0].message.content[:200])

FAQ

Claude vs Gemini questions.

Anything else? Ask our team and we’ll answer by email.

Is Claude or Gemini cheaper?

It depends on the tier. For 10,000 requests of 2,000 tokens in and 500 out on Zurelay: each lab's most capable model, Gemini 4 Argon costs 77% less than Claude Fable 5.1 ($36.00 against $157.50); coding and agents at volume, Gemini 3.8 Flash costs 65% less than Claude Sonnet 5.5 ($14.35 against $40.50); fast and low-cost, Claude Haiku 5.5 costs 76% less than Gemini 3.5 Flash-Lite ($1.80 against $7.60). Both are 46–65% below their labs' list prices.

Can I use Claude and Gemini with one API key?

Yes. One Zurelay key calls every Claude and Gemini model. With an OpenAI SDK, point it at https://api.zurelay.com/v1 and change only the model name to switch between them. Claude also answers on Anthropic's Messages API, for Claude Code and the Anthropic SDKs.

Which is better for coding?

Both labs build models for it: Anthropic describes Claude Opus 5.5 as built for long-running agentic coding, and Google built Gemini 3.8 Flash for long-horizon software engineering and autonomous agents. Gemini also reads audio and video, which Claude doesn't. Results vary by task, so run your own through both. On Zurelay that's a change of model name.

Are these the real Claude and Gemini models?

Yes. Each model is served over several routes run by independent sellers, and every route is tested before it serves requests and every day after, with identity, dated-knowledge and reasoning checks that catch a different or older model sold under the name you asked for.

More pricing

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer