GPT-3.5 Turbo (older v0613)

OpenAIopenai/gpt-3.5-turbo-0613Providers: 1
Inputi$1per 1M tokens
Outputi$2per 1M tokens
Contexti4K4,095 tokens
ReleasedJan 25, 2024Max output: 4K

Where it stands

Quality in independent tests against price, next to 135 other models. Up means more capable, left means cheaper.

100110120130140150160170$0.01$0.03$0.1$0.3$1$3$10$30$100Overall indexPrice per million tokens, log scale (3 parts input to 1 part output)↖ Cheaper and smarterGPT-3.5 Turbo (older v0613)
Scores: Epoch AI (CC BY 4.0). Prices: OpenRouter. View as a table

About this model

GPT-3.5 Turbo (older v0613) is an AI model from OpenAI, made available through the API on January 25, 2024. It can read up to 4,095 tokens in one request, roughly 8 pages of text, and write up to 3,685 tokens in a single answer.

Through the API it costs $1 per million input tokens and $2 per million output tokens. Its pricing sits in the middle of the market.

It can call tools and functions, so developers can connect it to search, databases or other software.

Quality scores

Rankings →
118.5Overall index · #131 of 136
  • GPQA DiamondVery hard multiple-choice questions in biology, physics and chemistry, written by PhD experts. Random guessing scores 25%.28.0%#111 of 116
  • AIME mathCompetition-level math problems in the style of the American Invitational Mathematics Examination. Share solved.2.2%#108 of 112
  • FrontierMathOriginal, unpublished math problems written by professional mathematicians, from advanced to research level. Share solved.0.0%#73 of 73

Benchmark data: Epoch AI, licensed CC BY 4.0

Where to use it

Companies that serve this model through an API: 1. Prices per million tokens, cheapest first.

ProviderInputiOutputiContextiUptime (24 h)i
Azure
$1$24K100.0%

Availability and prices come from OpenRouter’s public API and are refreshed daily. Uptime is the share of successful requests over the last 24 hours. Some providers run a compressed version of open models (fp8, int4), which is cheaper but can be slightly less accurate.

Use it in your code

Call GPT-3.5 Turbo (older v0613) through OpenRouter’s OpenAI-compatible API: create a key on openrouter.ai, then run one of these examples.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-3.5-turbo-0613", "messages": [{"role": "user", "content": "Hello! What can you do?"}]}'

The same code works with every model on this site: only the model ID changes. Many labs also offer their own API and SDK.

What it costs in practice

  • 1,000 chat replies
    ≈ 500 tokens in, 300 out each
    $1.10
  • Summarise a 100-page document
    ≈ 50,000 tokens in, 1,000 out
    $0.052
  • An app with 10,000 requests a day for a month
    ≈ 1,000 tokens in, 400 out each
    $540

Cost calculator →

Similar-priced alternatives

ModelInputiOutputiContexti
InklingThinking Machines Lab
$1$4.05512KCompare with ⇄
$1$2256KCompare with ⇄
$1$3256KCompare with ⇄
$1$5200KCompare with ⇄
Hermes 4 405BNous Research
$1$3128KCompare with ⇄
SonarPerplexity
$1$1127KCompare with ⇄

News about OpenAI

See all →

Frequently asked questions

How much does GPT-3.5 Turbo (older v0613) cost?
GPT-3.5 Turbo (older v0613) costs $1 per million input tokens and $2 per million output tokens through the API. For example, 1,000 chat replies of about 500 tokens in and 300 out cost around $1.10.
What is the context window of GPT-3.5 Turbo (older v0613)?
GPT-3.5 Turbo (older v0613) can read up to 4,095 tokens in one request, about 8 pages of text. It can write up to 3,685 tokens in a single answer.
Is GPT-3.5 Turbo (older v0613) open source?
No. GPT-3.5 Turbo (older v0613) is a closed model: its weights are not published, so you use it through OpenAI’s own apps and API, or through cloud providers.
Who makes GPT-3.5 Turbo (older v0613)?
GPT-3.5 Turbo (older v0613) is made by OpenAI. It became available through the API on January 25, 2024.
How good is GPT-3.5 Turbo (older v0613)?
GPT-3.5 Turbo (older v0613) has an overall index of 118.5 in Epoch AI’s independent tests, ranking #131 of 136 models we track.
Can GPT-3.5 Turbo (older v0613) read images?
No. GPT-3.5 Turbo (older v0613) only accepts text as input.
What are the alternatives to GPT-3.5 Turbo (older v0613)?
Models with a similar price from other companies include Inkling, Grok Build 0.1 and Relace Search. You can compare them side by side on this page.