tokenstat
tokenstat

OpenAI: GPT-5

openai/gpt-5 · rates as of · Benchmarks · AI plans · Calculator

Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows

Cheapest input
$0.625
$/MTok · OpenRouter
Cheapest output
$5
$/MTok
Context
400K
tokens
Sources
3
39 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ 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.

SourceProviderInputOutputCache readContext
OpenRoutercheapestopenai/gpt-5:batchOpenRouter$0.625$5$0.0625400K
LiteLLMopenai/gpt-5:batchN/A$0.625$5$0.0625N/A
models.devopenai/gpt-5Ofox$1$8$0.104400K
models.devgpt-5OpenCode Zen$1.07$8.50$0.107400K
models.devopenai/gpt-5Poe$1.10$9$0.11400K
LiteLLMdatabricks-gpt-5N/A$1.25$10$0.125N/A
LiteLLMdatabricks/databricks-gpt-5N/A$1.25$10$0.125N/A
models.devopenai/gpt-5Cloudflare$1.25$10$0.125128K
models.devopenai/gpt-5Eden AI$1.25$10$0.125400K
models.devopenai/gpt-5FastRouter$1.25$10$0.125400K
models.devopenai/gpt-5Impossibl$1.25$10$0.125400K
models.devopenai/gpt-5Kilo Gateway$1.25$10$0.125400K
models.devopenai/gpt-5LLM Gateway$1.25$10$0.125400K
models.devopenai/gpt-5Merge Gateway$1.25$10$0.125400K
models.devopenai/gpt-5NanoGPT$1.25$10$0.125400K
models.devopenai/gpt-5NEAR AI Cloud$1.25$10$0.125400K
models.devgpt-5OpenAI$1.25$10$0.125400K
OpenRouteropenai/gpt-5OpenRouter$1.25$10$0.125400K
models.devopenai/gpt-5OrcaRouter$1.25$10$0.125400K
models.devopenai/gpt-5Vercel AI Gateway$1.25$10$0.125400K
models.devopenai/gpt-5ZenMux$1.25$10$0.12400K
models.devgpt-5302.AI$1.25$10$0400K
models.devgpt-5Abacus$1.25$10$0.125400K
models.devgpt-5Azure$1.25$10$0.13400K
models.devgpt-5Azure$1.25$10$0.13400K
models.devgpt-5Helicone$1.25$10$0.125400K
models.devgpt-5DevPass (LLM Gateway)$1.25$10$0.125400K
models.devgpt-5Neon$1.25$10$0.125400K
models.devgpt-5SAP AI Core$1.25$10$0.125400K
models.devgpt-5-thinking302.AI$1.25$10$0400K
models.devdatabricks-gpt-5Databricks$1.25$10$0.125400K
LiteLLMgpt-5N/A$1.25$10$0.125N/A
LiteLLMgmi/openai/gpt-5N/A$1.25$10$0.125N/A
LiteLLMperplexity/openai/gpt-5N/A$1.25$10$0.125N/A
LiteLLMreplicate/openai/gpt-5N/A$1.25$10$0.125N/A
models.devgpt-5Cortecs$1.38$10.96$0.156400K
LiteLLMazure/eu/gpt-5N/A$1.38$11$0.1375N/A
LiteLLMeu/gpt-5N/A$1.38$11$0.1375N/A
LiteLLMus/gpt-5N/A$1.38$11$0.1375N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • In: file
  • Out: text
  • Out: image
Knowledge cutoff: 2024-09-30Released: 2025-08-08Family: gpt

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.

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.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.