OpenAI: GPT-5
Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $8.50 → $5
- ↓ lowerInput $1.07 → $0.625
- ↑ higherOutput $5 → $8.50
- ↑ higherInput $0.625 → $1.07
- ↓ lowerOutput $8.50 → $5
- ↓ lowerInput $1.07 → $0.625
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| OpenRoutercheapestopenai/gpt-5:batch | OpenRouter | $0.625 | $5 | $0.0625 | 400K |
| models.devgpt-5 | OpenCode | $1.07 | $8.50 | $0.107 | 400K |
| models.devopenai/gpt-5 | Poe | $1.14 | $9.09 | $0.1136 | 400K |
| LiteLLMdatabricks-gpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| LiteLLMdatabricks/databricks-gpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| models.devopenai/gpt-5 | AI/ML API | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Cloudflare | $1.25 | $10 | $0.125 | 128K |
| models.devopenai/gpt-5 | Eden AI | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | FastRouter | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Impossibl | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Kilo Gateway | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | LLM Gateway | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Merge Gateway | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | NanoGPT | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | NEAR AI Cloud | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Ofox | $1.25 | $10 | $0.13 | 400K |
| models.devgpt-5 | OpenAI | $1.25 | $10 | $0.125 | 400K |
| OpenRouteropenai/gpt-5 | OpenRouter | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | OrcaRouter | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | Prime Inference | $1.25 | $10 | $0 | 400K |
| models.devopenai/gpt-5 | Vercel AI Gateway | $1.25 | $10 | $0.125 | 400K |
| models.devopenai/gpt-5 | ZenMux | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | 302.AI | $1.25 | $10 | $0 | 400K |
| models.devgpt-5 | Abacus | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | AIHubMix | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | Azure | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | Azure | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | Helicone | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | DevPass (LLM Gateway) | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | Neon | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5 | SAP AI Core | $1.25 | $10 | $0.125 | 400K |
| models.devgpt-5-thinking | 302.AI | $1.25 | $10 | $0 | 400K |
| models.devauto/openai/gpt-5 | LowRouter | $1.25 | $10 | $0.125 | 400K |
| models.devdatabricks-gpt-5 | Databricks | $1.25 | $10 | $0.125 | 400K |
| LiteLLMgpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| LiteLLMgmi/openai/gpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| LiteLLMperplexity/openai/gpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| LiteLLMreplicate/openai/gpt-5 | N/A | $1.25 | $10 | $0.125 | N/A |
| models.devgpt-5 | Cortecs | $1.38 | $10.96 | $0.156 | 400K |
| LiteLLMazure/eu/gpt-5 | N/A | $1.38 | $11 | $0.1375 | N/A |
| LiteLLMeu/gpt-5 | N/A | $1.38 | $11 | $0.1375 | N/A |
| LiteLLMus/gpt-5 | N/A | $1.38 | $11 | $0.1375 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: pdf
- In: file
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence23i
- AA coding37.8i
- AA agentic0i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.