tokenstat
tokenstat

OpenAI: GPT-4 Turbo

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

Compact GPT model for low-latency assistance and high-volume workloads

Cheapest input
$9
$/MTok · models.dev
Cheapest output
$27
$/MTok
Context
128K
tokens
Offers
15
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-4-turboPoe$9$27$0128K
models.devopenai/gpt-4-turboCloudflare$10$30$0128K
models.devopenai/gpt-4-turboImpossibl$10$30$0128K
models.devopenai/gpt-4-turboKilo Gateway$10$30$0128K
models.devopenai/gpt-4-turboMerge Gateway$10$30$0128K
models.devopenai/gpt-4-turboNanoGPT$10$30$0128K
models.devgpt-4-turboOpenAI$10$30$1128K
OpenRouteropenai/gpt-4-turboOpenRouter$10$30$0128K
models.devopenai/gpt-4-turboOrcaRouter$10$30$0128K
models.devopenai/gpt-4-turboVercel AI Gateway$10$30$0128K
models.devgpt-4-turboAzure$10$30$0128K
models.devgpt-4-turboAzure$10$30$1128K
models.devgpt-4-turboLLM Gateway$10$30$0128K
LiteLLMgpt-4-turbo$10$30$1
LiteLLMvercel_ai_gateway/openai/gpt-4-turbo$10$30$1

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • Out: text
Knowledge cutoff: 2023-12Released: 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