LLM·Dex
Newsletter

Claude 3.5 Sonnet vs GPT-4.1

A complete head-to-head: pricing, context window, benchmarks, modality coverage, and openness, with a programmatic verdict synthesized from the underlying data.

Updated

Claude 3.5 Sonnet specs · GPT-4.1 specs
Verdict by category
  • PriceGPT-4.1

    GPT-4.1 is roughly 1.9× cheaper on output tokens ($8.00 vs $15.00 per 1M).

  • Context windowGPT-4.1

    GPT-4.1 accepts 1M tokens vs 200K, 5.0× the room for long documents and codebases.

  • BenchmarksClaude 3.5 Sonnet

    Claude 3.5 Sonnet leads in 1 of 1 shared benchmarks; the biggest gap is on HumanEval (Python coding), where it scores 92.0 vs 90.6.

  • ModalitiesTie

    Both handle text, vision.

  • OpennessTie

    Both are closed-weight, API-only.

On balance GPT-4.1 edges ahead, winning 2 of 5 categories against Claude 3.5 Sonnet's 1. GPT-4.1 is roughly 1.9× cheaper on output tokens ($8.00 vs $15.00 per 1M). GPT-4.1 accepts 1M tokens vs 200K, 5.0× the room for long documents and codebases.

Claude 3.5 Sonnet leads in 1 of 1 shared benchmarks; the biggest gap is on HumanEval (Python coding), where it scores 92.0 vs 90.6. Both target the same set of modalities (text, vision), so the deciding factors are price, context, and raw quality. Both are closed-weight, API-only.

GPT-4.1 is the newer of the two, released 6 months after Claude 3.5 Sonnet, which usually means a more recent knowledge cutoff and updated safety post-training. Claude 3.5 Sonnet is usually picked for coding llm and code review workloads, while GPT-4.1 sees more deployments in long context and rag. If pricing matters more than every last benchmark point, run the numbers in the calculator below before committing.

Side-by-side specs

SpecClaude 3.5 SonnetGPT-4.1
ProviderAnthropicOpenAI
ReleasedOct 2024Apr 2025
Modalitiestext, visiontext, vision
Context window200K tokens1M tokens
Max output,32.8K tokens
Input · 1M$3.00 / 1M tokens$2.00 / 1M tokens
Output · 1M$15.00 / 1M tokens$8.00 / 1M tokens
Knowledge cutoff,2024-06
Open weightsNoNo
API availableYesYes

Pricing at scale

What you'd actually pay at typical workloads. Numbers come from each model's published per-million-token rates.

  • Light usage, 100k in / 50k out per day$31.50 vs $18.00
  • Heavy usage, 1M in / 500k out per day$315 vs $180
  • RAG workload, 5M in / 200k out per day$540 vs $348

Light usage, 100k in / 50k out per day: $31.50 vs $18.00 per month, model B comes out ahead. Heavy usage, 1M in / 500k out per day: $315 vs $180 per month, model B comes out ahead. RAG workload, 5M in / 200k out per day: $540 vs $348 per month, model B comes out ahead.

Price calculator

Estimated spend for the listed models at your usage. Numbers are derived from each model's published per-million-token rates.

  • Claude 3.5 Sonnet$1.05
  • GPT-4.1$0.600

Benchmarks compared

Only sourced numbers. Where a benchmark is missing for one model we show the available value rather than fabricating the other.

Claude 3.5 SonnetGPT-4.1
  • MMLU,86.2
  • HumanEval92.090.6
Pick Claude 3.5 Sonnet if

Claude 3.5 Sonnet fits when…

  • Mature and battle-tested
  • Strong code
Pick GPT-4.1 if

GPT-4.1 fits when…

  • 1M-token context window, strong for long-doc workloads
  • Mature SDK and tooling integrations
  • Reliable JSON-mode and function-calling
  • Cost-sensitive workloads, 1.9× cheaper than Claude 3.5 Sonnet on output tokens.
  • Long-context tasks, handles 1M tokens vs 200K for Claude 3.5 Sonnet.
Don't want either?

Consider Claude Opus 4.7

Anthropic's mid-2026 flagship, ahead on SWE-bench, agent reliability, and writing quality.

See Claude Opus 4.7 specsClaude 3.5 Sonnet vs Claude Opus 4.7GPT-4.1 vs Claude Opus 4.7

Frequently asked

  • Is Claude 3.5 Sonnet or GPT-4.1 cheaper?
    GPT-4.1 is cheaper at $8.00 / 1M tokens per million output tokens, vs $15.00 / 1M tokens for Claude 3.5 Sonnet.
  • Which has the larger context window?
    GPT-4.1 accepts 1M tokens vs 200K for Claude 3.5 Sonnet.
  • Is Claude 3.5 Sonnet or GPT-4.1 better for coding?
    Both Claude 3.5 Sonnet and GPT-4.1 are competitive on coding benchmarks. See each model's individual spec page for HumanEval and SWE-bench scores where published. For an opinionated pick, consult our Best LLM for Coding ranking.
  • Are either of these models open source?
    Neither model ships open weights, both are accessible only via their respective providers' APIs.
  • When were Claude 3.5 Sonnet and GPT-4.1 released?
    Claude 3.5 Sonnet was released by Anthropic on 2024-10-22. GPT-4.1 was released by OpenAI on 2025-04-14.
Friday digest

The week's AI launches, in your inbox.

One short email every Friday, new models, leaks, and quietly-shipped APIs you missed.