Model Comparison

Claude 3.5 Sonnet vs GPT-4.1 nano

Anthropic vs OpenAI

OpenAI's GPT-4.1 nano costs less per intelligence point, even though Anthropic's Claude 3.5 Sonnet scores higher.

Data last updated March 4, 2026

GPT-4.1 nano delivers more intelligence per dollar, while Claude 3.5 Sonnet leads on raw benchmark scores. Claude 3.5 Sonnet costs $0.03 per request vs $0.0009 for GPT-4.1 nano (at 5K input / 1K output tokens). The question is whether Claude 3.5 Sonnet's higher scores justify the 33x price premium.

Benchmarks & Performance

Metric Claude 3.5 Sonnet GPT-4.1 nano
Intelligence Index 15.9 14.9
MMLU-Pro 0.8 0.7
GPQA 0.6 0.5
AIME 0.2 0.2
Context window 200,000 1,047,576

Pricing per 1M Tokens

List prices as published by the provider. Not adjusted for token efficiency.

Metric Claude 3.5 Sonnet GPT-4.1 nano
Input price / 1M tokens $3.00 $0.10
Output price / 1M tokens $15.00 $0.40
Cache hit price / 1M tokens $0.30 $0.02

Intelligence vs Price

10 15 20 25 30 35 40 $0.001 $0.002 $0.005 $0.01 $0.02 $0.05 Typical request cost (5K input + 1K output) Intelligence Index Gemini 2.5 Pro DeepSeek R1 0528 GPT-4.1 GPT-4.1 mini Claude 4 Sonnet... Claude 4.5 Sonn... Gemini 2.5 Flas... Grok 3 mini Rea... Claude 3.5 Sonnet GPT-4.1 nano
Claude 3.5 Sonnet GPT-4.1 nano Other models

Value Analysis

Cost per IQ point based on a typical request of 5,000 input and 1,000 output tokens.

Cheaper (list price)

GPT-4.1 nano

Higher Benchmarks

Claude 3.5 Sonnet

Better Value ($/IQ point)

GPT-4.1 nano

Claude 3.5 Sonnet

$0.0019 / IQ point

GPT-4.1 nano

$0.00006 / IQ point

Frequently Asked Questions

How much cheaper is GPT-4.1 nano than Claude 3.5 Sonnet?

GPT-4.1 nano is dramatically cheaper — 33x less per request than Claude 3.5 Sonnet. GPT-4.1 nano is cheaper on both input ($0.1/M vs $3.0/M) and output ($0.4/M vs $15.0/M). At a fraction of the cost, GPT-4.1 nano saves significantly in production workloads. This comparison assumes a typical request of 5,000 input and 1,000 output tokens (5:1 ratio). Actual ratios vary by workload — chat and completion tasks typically run 2:1, code review around 3:1, document analysis and summarization 10:1 to 50:1, and embedding workloads are pure input with no output tokens.

Which benchmarks does Claude 3.5 Sonnet win, and which does GPT-4.1 nano win?

Claude 3.5 Sonnet scores higher overall (15.9 vs 14.9). Claude 3.5 Sonnet leads on MMLU-Pro (0.77 vs 0.66) and GPQA (0.6 vs 0.51), while GPT-4.1 nano leads on AIME (0.24 vs 0.16). If mathematical reasoning matters, GPT-4.1 nano's AIME score of 0.24 gives it an edge.

How much more context can GPT-4.1 nano handle than Claude 3.5 Sonnet?

GPT-4.1 nano has a much larger context window — 1,047,576 tokens vs Claude 3.5 Sonnet at 200,000 tokens. That's roughly 1,396 vs 266 pages of text. GPT-4.1 nano's window can handle entire codebases or book-length documents; Claude 3.5 Sonnet works better for shorter inputs.

Is GPT-4.1 nano worth choosing over Claude 3.5 Sonnet on value alone?

GPT-4.1 nano offers dramatically better value — $0.00006 per intelligence point vs Claude 3.5 Sonnet at $0.0019. GPT-4.1 nano is cheaper, which offsets Claude 3.5 Sonnet's higher benchmark scores to deliver more value per dollar. If raw benchmark scores matter less than cost for your use case, GPT-4.1 nano is the efficient choice.

How does prompt caching affect Claude 3.5 Sonnet and GPT-4.1 nano pricing?

With prompt caching, GPT-4.1 nano is dramatically cheaper — 31x less per request than Claude 3.5 Sonnet. Caching saves 45% on Claude 3.5 Sonnet and 42% on GPT-4.1 nano compared to standard input prices. Both models benefit from caching at similar rates, so the uncached price comparison holds.

Pricing verified against official vendor documentation. Updated daily. See our methodology.

Related Comparisons

Stop guessing. Start measuring.

Create an account, install the SDK, and see your first margin data in minutes.

See My Margin Data

No credit card required