Completion
DocsServerless InferenceCompletion

Completion

This endpoint generates text completions for a given prompt.

Global (US)
https://api.geodd.io/inference/v1/completions
Europe (EU)
https://eu.api.geodd.io/inference/v1/completions

Authorizations

Authorization string header required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model string required

Model name to use for generating completions.

Example: meta-llama/Llama-3.1-405B-instruct
prompt string | array required

The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays.

max_tokens integer optional

The maximum number of tokens to generate in the completion. The total length of input tokens and generated tokens is limited by the model's context length.

Responses

200
OK
Request processed successfully. Returns a completion object.
401
Unauthorized
Invalid or missing API Key. Check the Authorization header.
429
Too Many Requests
Token limit exceeded. Upgrade to a dedicated instance for higher limits.

Example Request

Example RequestShell / 8 lines
curl --location 'https://api.geodd.io/inference/v1/completions' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
    "model": "meta-llama/Llama-3.1-405B-instruct",
    "prompt": "How big is earth?",
    "max_tokens": 200
}'
Next
Embedding