OpenAI · Released Oct 6, 2025
GPT-5 Pro
GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reasoning, instruction following, and...
- Top 21%Chess Puzzles
- Top 30%SimpleBench
- Top 32%Humanity's Last Exam
- Released
- Oct 6 2025
- Context window
- 400K 128K out
- Input / 1M tokens
- $15.00 from $13.64
- Output / 1M tokens
- $120.00 from $109.09
Where to run it
16 providers compared
Cheapest: Poe at $13.64 / $109.09 per 1M input / output tokens — 34% less than the priciest option.
| Provider | Input | Output | Cache read | Context | Max output | Uptime | vs. best |
|---|---|---|---|---|---|---|---|
| Poe | $13.64 | $109.09 | — | 400K | 128K | — | Cheapest |
| Jiekou.AI | $14.25 | $114.00 | — | 400K | 272K | — | +5% |
| OpenAI | $15.00 | $120.00 | — | 400K | 128K | 100%24h | +10% |
| Helicone | $15.00 | $120.00 | — | 128K | 33K | — | +10% |
| NanoGPTno tool calling | $15.00 | $120.00 | $1.50 | 400K | 128K | — | +10% |
| Kilo Gateway | $15.00 | $120.00 | — | 400K | 128K | — | +10% |
| Vercel AI Gateway | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| LLM Gateway | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| 302.AI | $15.00 | $120.00 | $0.005 | 400K | 272K | — | +10% |
| Azure | $15.00 | $120.00 | — | 400K | 128K | — | +10% |
| Azure Cognitive Services | $15.00 | $120.00 | — | 400K | 128K | — | +10% |
| DevPass (LLM Gateway) | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| Impossibl | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| OrcaRouter | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| Eden AI | $15.00 | $120.00 | — | 400K | 272K | — | +10% |
| AI/ML API | $20.63 | $165.05 | — | 400K | 272K | — | +51% |
Value
Price vs. performance
GPT-5 Pro Other OpenAI Other labs Value frontier · Humanity's Last Exam vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.
Benchmarks
7 benchmark scores
| Benchmark | Score | Rank | Leader |
|---|---|---|---|
| Humanity's Last ExamReasoning & knowledge · Expert questions across 100+ subjects | 31.6% | #10of 32 | GPT-6 Astra54.8% |
| ARC-AGI-2Reasoning & knowledge · Few-shot abstract reasoning on grid puzzles | 18.3% | #46of 75 | GPT-6 Astra95.0% |
| ARC-AGI-1Reasoning & knowledge · Pattern induction from input–output examples | 70.2% | #46of 75 | Gemini 4 Argon98.5% |
| SimpleBenchReasoning & knowledge · Common-sense trick questions about space, time and people | 61.6% | #17of 58 | Claude Fable 581.9% |
| Chess PuzzlesReasoning & knowledge · Find the single best move in 100 new puzzles | 48.0% | #17of 83 | GPT-6 Astra76.0% |
| FrontierMathMaths · Expert-written problems, undergrad to early research (tiers 1–3) | 55.8% | #46of 87 | GPT-6.1 Sol93.7% |
| FrontierMath Tier 4Maths · Exceptionally hard research-level problems | 19.5% | #47of 64 | GPT-6.1 Sol100.0% |
Specs
Details
- Model ID
openai/gpt-5-pro- Developer
- OpenAI
- Release date
- Oct 6, 2025 ·
- Context window
- 400,000 tokens
- Max output
- 128,000 tokens
- API price
- $15.00 / $120.00 per 1M input / output tokens
- Providers
- 16
- Input types
- image, text, file
- Reasoning
- Yes
- Tool calling
- Yes
- Open weights
- No
- Free tier
- No
Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.