GPT-5 (medium)
AI model by OpenAI. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. GPT-5 (medium) is positioned in the mid-tier at $10.00/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-5 (medium) reports 99 tok/s output speed and 26680ms 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 (medium) costs $2.25 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 (medium)Current | $1.25 | $10.00 | 99 tok/s |
| Gemini 2.5 Pro Preview (May' 25) | $1.25 | $10.00 | — |
| Nova 2.0 Pro Preview (medium) | $1.25 | $10.00 | 115 tok/s |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | $2.00 | $10.00 | 76 tok/s |
| Gemini 2.5 Pro | $1.25 | $10.00 | 133 tok/s |
| Command A | $2.50 | $10.00 | 60 tok/s |