Claude Sonnet 5 vs GPT-4.1
Anthropic vs OpenAI · Prices checked 12 August 2026
GPT-4.1 is 14 per cent cheaper on blended cost, $3.80 per million tokens against $4.40. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.300 on Claude Sonnet 5.
Both offer the same 1,000,000-token context window. Claude Sonnet 5 was released Jun 2026; GPT-4.1 Apr 2025.
Pricing and capacity
| Metric | Claude Sonnet 5 | GPT-4.1 | Difference |
|---|---|---|---|
| Input / 1M tokens | $2.00 | $2.00 | level |
| Output / 1M tokens | $10.00 | $8.00 | 20% |
| Blended · 70/30calculated | $4.40 | $3.80 | 14% |
| Blended · 50/50calculated | $6.00 | $5.00 | 17% |
| Blended · 80/20calculated | $3.60 | $3.20 | 11% |
| Blended · 20/80calculated | $8.40 | $6.80 | 19% |
| Job cost · 100K + 10Kcalculated | $0.300 | $0.280 | 7% |
| Job cost · 1M + 100Kcalculated | $3.00 | $2.80 | 7% |
| Context window | 1,000,000 | 1,000,000 | level |
Input and output rates are as published by each provider. Blended and job-cost rows are calculated comparison metrics, not published prices — how they are derived.
Benchmarks
These two models do not currently report scores on any of the same benchmark suites, so there is no like-for-like capability comparison to show. Rather than pad the page with one-sided numbers, the benchmark leaderboards list every score we do hold.
What each model is for
Claude Sonnet 5
Anthropic · Balanced
The most agentic Sonnet Anthropic has shipped: it plans, drives tools like browsers and terminals, and runs autonomously at a level that previously needed a larger model, with performance close to Opus 4.8 at a fraction of the price. Launch pricing is $2/$10 per MTok through 31 August 2026, after which it moves to $3/$15.
- Autonomous multi-step agent runs
- Browser and terminal tool use
- Near-Opus performance at Sonnet pricing
- 1M-token context
Frequently asked questions
Which is cheaper, Claude Sonnet 5 or GPT-4.1?
GPT-4.1 is 14 per cent cheaper on blended cost, $3.80 per million tokens against $4.40. A single 100K-input, 10K-output job costs $0.280 on GPT-4.1 against $0.300 on Claude Sonnet 5. Blended cost weights input at 70% and output at 30%; price your own token split for an exact answer, since the cheaper model on a blended basis is not always cheaper for your workload.
Which has the larger context window, Claude Sonnet 5 or GPT-4.1?
Both offer the same 1,000,000-token context window. The context window caps everything in a single request: prompt, retrieved documents, conversation history and the model’s own output all share it.
Can I compare Claude Sonnet 5 and GPT-4.1 on my own numbers?
Yes. Open both in the side-by-side comparison tool to see every field at once, or use the token calculator to price your actual prompt and monthly request volume against each model. Both are free and need no sign-up.
Price it for your own workload
Related matchups
Terms used on this page
Prices and scores are recomputed on every deploy from the catalogue. Prices checked 12 August 2026.