tokenstat
tokenstat

OpenAI: GPT-4

openai/gpt-4 · rates as of · Benchmarks · Plans · Calculator

GPT model for general reasoning, writing, coding, and tool-assisted tasks

Cheapest input
$30
$/MTok · models.dev
Cheapest output
$60
$/MTok
Context
8K
tokens
Offers
9
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestopenai/gpt-4Cloudflare$30$60$08K
models.devopenai/gpt-4Kilo Gateway$30$60$08K
models.devopenai/gpt-4Merge Gateway$30$60$08K
models.devgpt-4OpenAI$30$60$38K
OpenRouteropenai/gpt-4OpenRouter$30$60$38K
models.devopenai/gpt-4OrcaRouter$30$60$08K
models.devgpt-4LLM Gateway$30$60$08K
LiteLLMgpt-4$30$60$3
LiteLLMazure/gpt-4$30$60$3

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: pdf
  • Out: text
Knowledge cutoff: 2023-11Released: 2023-11-06Family: gpt

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.

Sources: Arena AI, Artificial Analysis. See /benchmarks.

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash