tokenstat
tokenstat

OpenAI: GPT-3.5 Turbo Instruct

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

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

Cheapest input
$1.40
$/MTok · models.dev
Cheapest output
$1.80
$/MTok
Context
4K
tokens
Offers
8
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-turbo-instructPoe$1.40$1.80$04K
models.devopenai/gpt-3.5-turbo-instructKilo Gateway$1.50$2$04K
OpenRouteropenai/gpt-3.5-turbo-instructOpenRouter$1.50$2$04K
models.devgpt-3.5-turbo-instructAzure$1.50$2$04K
models.devgpt-3.5-turbo-instructAzure$1.50$2$04K
LiteLLMopenai/gpt-3.5-turbo-instruct$1.50$2$0.15
LiteLLMgpt-3.5-turbo-instruct$1.50$2$0.15
LiteLLMvercel_ai_gateway/openai/gpt-3.5-turbo-instruct$1.50$2$0.15

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: pdf
  • In: image
  • Out: text
Knowledge cutoff: 2021-09-30Released: 2023-09-28Family: gpt

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