Original GPT-5 workhorse for reasoning, coding, writing, and tool workflowsGPT-5 by openai is offered by 41 providers on this page. Public prices are shown for 38 of them. Its official list price is $1.25 per 1M input tokens and $10.00 per 1M output tokens. Prices vary about 2.3× across the providers that host it.
Median output speed is 106 tokens per second, with 77.18s to the first token.
The context window is 400,000 tokens at the reference host, but hosts report different limits, from 128,000 to 400,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-09-30.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OpenCode | Gateway | $1.07 | $8.50 | $0.11 | — | 400,000 | 128,000 | |
| Poe | Gateway | $1.14 | $9.09 | $0.11 | — | 400,000 | 128,000 | |
| OpenAIOfficial | First-party | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| LLM Gateway | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| LLM Gateway | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| 302.AI | Gateway | $1.25 | $10.00 | — | — | 400,000 | 128,000 | |
| 302.AI gpt-5-thinking | Gateway | $1.25 | $10.00 | — | — | 400,000 | 128,000 | |
| DigitalOcean openai-gpt-5 | Cloud | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| LowRouter | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 | |
| NanoGPT | Gateway | $1.25 | $10.00 | $0.13 | — | 400,000 | 128,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 41 providers.
3 / 41 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | OpenAI | $2.50 | $20.00 | $0.25 | — |
| flex | OpenAI | $0.63 | $5.00 | $0.063 | — |
| fast | Databricks | $2.50 | $20.00 | $0.25 | — |
| fast | Vercel AI Gateway | $2.50 | $20.00 | $0.25 | — |
| flex | Vercel AI Gateway | $0.63 | $5.00 | $0.063 | — |
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Aider Polyglot | — | 88 | percent correct | Source ↗ |
| SWE-Bench Pro | dataset: public | 41.78 | resolve rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.