GPT-5.4 (Non-reasoning)
AI model by OpenAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. GPT-5.4 (Non-reasoning) is a premium-tier model from OpenAI at $15.00/M output tokens. Benchmark scores (see above) suggest it targets workloads where correctness matters more than cost — long-running agents, code generation at scale, and complex multi-step reasoning.
Latency. On latency, GPT-5.4 (Non-reasoning) reports 90 tok/s output speed and 810ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.
Cost model. For a workload of 1M input tokens + 100K output tokens, GPT-5.4 (Non-reasoning) costs $4.00 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-5.4 (Non-reasoning)Current | $2.50 | $15.00 | 90 tok/s |
| Claude 3.5 Sonnet (Oct '24) | $3.00 | $15.00 | — |
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | $3.00 | $15.00 | 43 tok/s |
| Kimi K3 (low) | $3.00 | $15.00 | 36 tok/s |
| Grok 4 | $3.00 | $15.00 | — |
| Command-R+ (Apr '24) | $3.00 | $15.00 | — |