flagship
Gpt 5 vs Gpt 4.1
Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.
Specifications
| Feature | Gpt 5 | Gpt 4.1 |
|---|---|---|
| Provider | openai | openai |
| Model ID | gpt-5 | gpt-4.1 |
| Input / 1M tokens | $1.25 (38% cheaper) | $2.00 |
| Output / 1M tokens | $10.00 | $8.00 (20% cheaper) |
| Cached input / 1M | $0.13 | $0.50 |
| Context window | 272kk tokens | 1048kk tokens |
| Max output | 128kk tokens | 33kk tokens |
| Vision | ✅ | ✅ |
| Function calling | ✅ | ✅ |
| Prompt caching | ✅ | ✅ |
| Web search | ✅ | ✅ |
| JSON schema | ✅ | ✅ |
Monthly cost comparison
No cache discount applied — pure token costs at three usage scales.
| Scale | Gpt 5 | Gpt 4.1 | Winner |
|---|---|---|---|
| Small 1M in / 0.2M out | $3.25 | $3.60 | Gpt 5 saves 10% |
| Medium 10M in / 2M out | $32.50 | $36.00 | Gpt 5 saves 10% |
| Large 100M in / 20M out | $325 | $360 | Gpt 5 saves 10% |
Category winners
Cheapest input
Gpt 5
$1.25/M
· 38% less than the other
Cheapest output
Gpt 4.1
$8.00/M
· 20% less than the other
Larger context
Gpt 4.1
1048kk tokens · 285% larger window
More features
Gpt 5
5 / 5 capabilities
(tied)
Better for…
High-volume RAG & repeated context
$0.13/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gpt 5
Short interactions & high-throughput APIs
$8.00/M output — 20% cheaper on output at scale
Gpt 4.1
Long-document processing & large codebases
1048k context window vs 272k — 285% larger context
Gpt 4.1
Deep-dive on each model
Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.