Claude Sonnet 5 (batch) vs GPT-4.1
Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (batch) (Anthropic) and GPT-4.1 (OpenAI). Green cells mark the better value in each row.
Prices updated Sep 19, 2026, 7:21 PM UTC · refreshed hourly
| Claude Sonnet 5 (batch) Anthropic | GPT-4.1 OpenAI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $1.00 | $2.00 |
| Output $/1M | $5.00 | $8.00 |
| Blended $/1M (3:1) | $2.00 | $3.50 |
| RAG example (30K in / 2K out) | $0.04 | $0.076 |
| Quality & speed | ||
| Intelligence Index | 38.4 | 12.7 |
| Coding Index | 71.5 | — |
| Agentic Index | 44.3 | — |
| Output speed (tok/s) | 86 | 0 |
| Time to first token | 120.21s | 0s |
| Specs | ||
| Context window | 1M | 1.05M |
| Input modalities | text, image, file | image, text, file |
FAQ
Which is cheaper, Claude Sonnet 5 (batch) or GPT-4.1?
Claude Sonnet 5 (batch) has the lower blended API price at $2.00 per 1M tokens (3:1 input:output mix), versus $3.50 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), Claude Sonnet 5 (batch) costs about $0.04 per request versus $0.076. Also compare context windows: Claude Sonnet 5 (batch) offers 1M and GPT-4.1 offers 1.05M.
Which scores higher on Artificial Analysis benchmarks?
Claude Sonnet 5 (batch) leads on the Artificial Analysis Intelligence Index (38.4 vs 12.7). Check coding and agentic indices on this page for workload-specific tradeoffs.