tokenstat
tokenstat

OpenAI: GPT-3.5 Turbo

openai/gpt-3.5-turbo · rates as of · Benchmarks · Plans · Calculator

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

Cheapest input
$0.45
$/MTok · models.dev
Cheapest output
$1.40
$/MTok
Context
16K
tokens
Offers
16
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-3.5-turboPoe$0.45$1.40$016K
models.devopenai/gpt-3.5-turboCloudflare$0.5$1.50$1.2516K
models.devopenai/gpt-3.5-turboImpossibl$0.5$1.50$016K
models.devopenai/gpt-3.5-turboKilo Gateway$0.5$1.50$016K
models.devopenai/gpt-3.5-turboMerge Gateway$0.5$1.50$016K
models.devopenai/gpt-3.5-turboNanoGPT$0.5$1.50$016K
models.devgpt-3.5-turboOpenAI$0.5$1.50$016K
OpenRouteropenai/gpt-3.5-turboOpenRouter$0.5$1.50$016K
models.devopenai/gpt-3.5-turboOrcaRouter$0.5$1.50$016K
models.devopenai/gpt-3.5-turboVercel AI Gateway$0.5$1.50$016K
models.devgpt-3.5-turboLLM Gateway$0.5$1.50$016K
LiteLLMgpt-3.5-turbo$0.5$1.50$0.05
LiteLLMazure/gpt-3.5-turbo$0.5$1.50$0.05
LiteLLMvercel_ai_gateway/openai/gpt-3.5-turbo$0.5$1.50$0.05
LiteLLMopenai/gpt-3.5-turbo$1.50$2$0.15
LiteLLMopenrouter/openai/gpt-3.5-turbo$1.50$2$0.15

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: pdf
  • In: image
  • Out: text
Knowledge cutoff: 2021-09-01Released: 2023-03-01Family: 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