This is the main interface to OpenAI's models,
using the responses API. You can use this to access OpenAI's latest
models and features like image generation and web search. If you need to use
an OpenAI-compatible API from another provider, or the chat completions
API with OpenAI,use chat_openai_compatible() instead.
Note that a ChatGPT Plus membership does not grant access to the API. You will need to sign up for a developer account (and pay for it) at the developer platform.
Usage
chat_openai(
system_prompt = NULL,
base_url = "https://api.openai.com/v1",
api_key = NULL,
credentials = NULL,
model = NULL,
params = NULL,
api_args = list(),
api_headers = character(),
service_tier = c("auto", "default", "flex", "priority"),
echo = c("none", "output", "all")
)
models_openai(
base_url = "https://api.openai.com/v1",
api_key = NULL,
credentials = NULL
)Arguments
- system_prompt
A system prompt to set the behavior of the assistant.
- base_url
The base URL to the API endpoint.
- api_key
- credentials
Override the default credentials. You generally should not need this argument; instead set the
OPENAI_API_KEYenvironment variable. The best place to set this is in.Renviron, which you can easily edit by callingusethis::edit_r_environ().If you do need additional control, this argument takes a zero-argument function that returns either a string (the API key), or a named list (added as additional headers to every request).
- model
The model to use for the chat (defaults to "gpt-6.1-terra"). We regularly update the default, so we strongly recommend explicitly specifying a model for anything other than casual use. Use
models_openai()to see all options.- params
Common model parameters, usually created by
params().- api_args
Named list of arbitrary extra arguments appended to the body of every chat API call. Combined with the body object generated by ellmer with
modifyList().- api_headers
Named character vector of arbitrary extra headers appended to every chat API call.
- service_tier
Request a specific service tier. There are four options:
"auto"(default): uses the service tier configured in Project settings."default": standard pricing and performance."flex": slower and cheaper."priority": faster and more expensive.
- echo
One of the following options:
none: don't emit any output (default when running in a function).output: echo text and tool-calling output as it streams in (default when running at the console).all: echo all input and output.
Note this only affects the
chat()method.
Value
A Chat object.
See also
Other chatbots:
chat_anthropic(),
chat_aws_bedrock(),
chat_azure_openai(),
chat_cloudflare(),
chat_databricks(),
chat_deepseek(),
chat_github(),
chat_google_gemini(),
chat_groq(),
chat_huggingface(),
chat_lmstudio(),
chat_mistral(),
chat_ollama(),
chat_openai_compatible(),
chat_openrouter(),
chat_perplexity(),
chat_portkey(),
chat_posit()
Examples
chat <- chat_openai()
#> Using model = "gpt-6.1-terra".
chat$chat("
What is the difference between a tibble and a data frame?
Answer with a bulleted list
")
#> - **Relationship:** A tibble is a modern type of R data frame provided by the
#> **tibble** package. It inherits from `data.frame`, so most data-frame functions
#> work with it.
#> - **Printing:** Tibbles display a preview of rows and columns, along with
#> column types. Data frames typically print more of their contents.
#> - **Subsetting:** `[` always returns a tibble, even when selecting one column.
#> A data frame may simplify the result to a vector.
#> - **Column names:** Tibbles preserve nonstandard names, such as names
#> containing spaces. Data frames normally adjust them by default.
#> - **Column access:** Tibbles do not support partial matching with `$` and warn
#> when a column does not exist. Data frames can partially match names and return
#> `NULL` for missing columns.
#> - **Recycling:** Tibbles recycle only length-one inputs when creating columns;
#> data frames allow more permissive recycling.
chat$chat("Tell me three funny jokes about statisticians")
#> - Why did the statistician break up with their partner? They couldn’t find a
#> significant relationship.
#> - A statistician drowned crossing a river that was, on average, three feet
#> deep.
#> - Why don’t statisticians trust atoms? They make up everything—and the sample
#> size is suspiciously large.
