GPT-4.1
AI model by OpenAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. GPT-4.1 is positioned in the mid-tier at $8.00/M output tokens. The benchmark profile is balanced — scoring across standard tests — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, GPT-4.1 reports 142 tok/s output speed and 870ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, GPT-4.1 costs $2.80 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
GPT-4.1Current | $2.00 | $8.00 | 142 tok/s |
| Jamba 1.5 Large | $2.00 | $8.00 | — |
| Qwen3.6 Max Preview | $1.30 | $7.80 | 61 tok/s |
| Qwen3 235B A22B (Reasoning) | $0.70 | $8.40 | 61 tok/s |
| Qwen3 Coder 480B A35B Instruct | $1.50 | $7.50 | 66 tok/s |
| Mistral Medium | $1.50 | $7.50 | 135 tok/s |