Skip to main content
POST
/
ai
/
v2
/
chat
/
completions
curl --request POST \
  --url https://platform.ai.gloo.com/ai/v2/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "messages": [
    {
      "role": "user",
      "content": "What does the Bible say about forgiveness?"
    }
  ],
  "auto_routing": true,
  "tradition": "evangelical",
  "temperature": 0.7,
  "max_tokens": 1024
}
'
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "gloo-anthropic-claude-3-sonnet",
  "routing_mechanism": "auto_routing",
  "routing_tier": "standard",
  "routing_confidence": 0.92,
  "tradition": "evangelical",
  "provider": "anthropic",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "The Bible speaks extensively about forgiveness...",
        "role": "assistant"
      }
    }
  ],
  "usage": {
    "completion_tokens": 150,
    "prompt_tokens": 25,
    "total_tokens": 175
  }
}

Authorizations

​
Authorization
string
header
required

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

Body

application/json

Request body for the completions v2 endpoint. Exactly one routing mechanism (auto_routing, model, or model_family) must be specified.

​
messages
LlmMessage · object[]
required

Chat message history with role and content fields.

​
auto_routing
boolean

Enables intelligent model selection. When true, the system analyzes queries to select the optimal model tier balancing speed versus capability. Mutually exclusive with model and model_family.

​
model
string

Specific Gloo model identifier (e.g., gloo-openai-gpt-5-pro). Provides full control and reproducibility. Mutually exclusive with auto_routing and model_family.

​
model_family
enum<string>

Provider family for model selection. The system optimizes model choice within that family. Mutually exclusive with auto_routing and model.

Available options:
openai,
anthropic,
google,
open source
​
tradition
enum<string>

Theological perspective to apply. Options: evangelical, catholic, mainline. Omit for general Christian perspective.

Available options:
evangelical,
catholic,
mainline,
not_faith_specific
​
stream
boolean
default:false

Enables streaming responses. When true, responses are sent as server-sent events as tokens are generated.

​
temperature
number
default:0.7

Sampling temperature controlling randomness. Higher values (e.g., 1.5) make output more random, lower values (e.g., 0.2) make it more deterministic.

Required range: 0 <= x <= 2
​
max_tokens
integer

Maximum number of tokens to generate in the response.

Required range: x >= 1
​
tools
Tool · object[]

Function calling definitions. Each tool includes type, name, description, and parameters schema.

​
tool_choice
default:none

Controls which tool (if any) the model should use.

Available options:
none,
auto,
required

Response

Successful completion response

Response from the completions v2 endpoint.

​
id
string

Unique completion identifier.

​
object
string
default:chat.completion

Object type, always 'chat.completion'.

​
created
integer

Unix timestamp of when the completion was created.

​
model
string

The model that was selected and used for the completion.

​
routing_mechanism
string

The routing method used: auto_routing, model_selection, or provider_selection.

​
routing_tier
string

The performance tier assigned by the routing system.

​
routing_confidence
number

Confidence score for the routing decision (0.0 to 1.0).

​
tradition
string

The theological perspective that was applied to the response.

​
provider
string

The model provider name (e.g., openai, anthropic, google).

​
choices
CompletionsV2Choice · object[]

List of completion choices.

​
usage
CompletionsV2Usage · object

Token consumption metrics.