Ask a model through one of the project's routes

post/models/v1/chat/completions

Ask a model through one of the project's routes. The body and the answer follow the OpenAI chat completions format; model is a route name from the model list, never a model's own name. With stream: true the answer arrives as server-sent events. Uses the project's token allowance. The answer carries cost.usd, what the call cost; a stream carries it in a last piece when stream_options.include_usage is set. purpose is a short tag of your own that the day's usage is counted under.

Before you call

Credential: Authorization: Bearer $KEY
Scope: models:write
Sdk: models.completion.create
Cli: models completion create

Request bodyapplication/json, required

modelstringrequired
At most 80 characters.
messageslist of objectrequired
- rolestringrequired
  At most 20 characters.
streamboolean or null
ninteger or null
max_tokensinteger or null
max_completion_tokensinteger or null
stream_optionsobject or null
purposestring or null

Responses

200text/event-stream
Success
string
400application/json
The request was malformed
- errorstringrequired
- messagestring
401application/json
No valid credential
- errorstringrequired
- messagestring
403application/json
The credential lacks the scope, origin or address
- errorstringrequired
- messagestring
429application/json
Over the key's rate limit; see Retry-After
- errorstringrequired
- messagestring

Example request

curl -X POST 'https://api.rivier.ai/models/v1/chat/completions' \
  -H 'Authorization: Bearer $KEY' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "string",
  "messages": [
    {
      "role": "string"
    }
  ]
}'

$KEY stands for your own key. No key is shown or kept on this site.

This page as Markdown