GPT-5.
OpenAI's frontier multimodal reasoning model.
No self-host path — closed weights.
GPT-5's weights aren't published. Use it via the access providers below.
Cheapest hosted endpoints.
What it's best at.
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 30.3 | — | 14782 ms |
Variants in the GPT family.
Frequently asked.
How do I run GPT-5?
Where can I access GPT-5?
How much does it cost to run GPT-5?
Is GPT-5 open-source or proprietary?
What it costs per month across providers.
Estimate your monthly bill for GPT-5 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
What it's best at.
Scores normalised against benchmark ceilings (100 = perfect). Coloured by tier — coral 80+ frontier, lavender 65+ strong, sage 50+ solid, slate below.
Published scores.
| Benchmark | Score | Source |
|---|---|---|
| GPQA | 71.0 | official ↗ |
| MATH | 96.0 | official ↗ |
| MMLU | 91.0 | official ↗ |
| MMMU | 78.0 | official ↗ |
| MMLU-Pro | 87.5 | official ↗ |
| HumanEval | 93.2 | official ↗ |
| SWE-bench | 74.9 | official ↗ |
Independent rankings.
About GPT-5.
GPT-5 is OpenAI's flagship model, released August 2025 as a unified replacement for the o3/4o/o3-mini split. It introduces dynamic routing between fast and deliberative modes — the API picks the right one per prompt, with optional reasoning_effort overrides. Supports 256K context, vision inputs, function calling, structured outputs, and built-in code interpreter. Leads MMLU-Pro and GPQA benchmarks; trades the SWE-bench top spot with Claude Sonnet 4.6. Available via OpenAI's API, ChatGPT, Azure OpenAI Service, and (mirrored) on aggregators like OpenRouter.