Skip to main content

​
Chat Completions

POST /api/v1/chat/completions
Not all models support every option beyond the basic request. Check the Model Library for model-specific compatibility. Open Model Library.

​
Base URL

https://app.eigenai.com

​
Authentication

Send your API key in the Authorization header as a Bearer token. 
Authorization: Bearer YOUR_API_KEY

​
Parameters

​
Common

NameTypeRequiredDescription
modelstringRequiredThe model ID to use. Find supported models in the Model Library.
messagesarrayRequiredConversation history as an array of { role, content } items.

​
Conditional

These options are not supported by every model. Use the Model Library to confirm compatibility.

​
Generation Controls

Common tuning knobs for output length and randomness (availability varies by model).
NameTypeRequiredDescription
temperaturenumberOptionalControls randomness/creativity. Higher values produce more varied outputs.
max_tokensnumberOptionalMaximum number of tokens to generate in the response.
top_pnumberOptionalNucleus sampling. Limits token selection to the smallest set with cumulative probability top_p.
top_knumberOptionalTop-k sampling. Limits token selection to the top k candidates.
min_pnumberOptionalMinimum probability threshold sampling (if supported).
repetition_penaltynumberOptionalPenalizes repeating tokens (if supported).

​
Streaming

Receive partial outputs incrementally.
NameTypeRequiredDescription
streambooleanOptionalSet to true to stream output via server-sent events (SSE).

​
Vision Input (Multi-part Message Content)

Some models accept mixed text + image inputs by using an array for content on a message.
NameTypeRequiredDescription
messages[].contentstring|arrayOptionalFor vision requests, content can be an array of parts like { type: "text" } and { type: "image_url" }.

​
Examples

​
Basic request

Send a list of messages and receive a single response. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 2000,
    "stream": false
  }'

​
Streaming (SSE)

Stream partial output tokens as SSE events. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

# Streaming uses Server-Sent Events (SSE). This prints raw SSE frames.
curl -N -X POST https://app.eigenai.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL",
    "messages": [
      {"role": "user", "content": "Write a 1-paragraph product update."}
    ],
    "stream": true
  }'

​
Vision input (text + image)

Send multi-part message content with text and image URLs. 
# Select a model in the Model Library: https://app.eigenai.com/model-library

curl -X POST https://app.eigenai.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Describe the image."},
          {"type": "image_url", "image_url": {"url": "https://example.com/image.png"}}
        ]
      }
    ],
    "max_tokens": 500,
    "stream": false
  }'