Skip to main content
POST
/
v1
/
chat
curl --request POST \
  --url https://api.gigabrain.gg/v1/chat \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "message": "Should I long or short ETH right now? Check technicals, funding, and macro. Respond as JSON with: direction, entry_price, stop_loss, take_profit_1, take_profit_2, risk_reward_ratio, confidence, reasoning"
}
'
{
  "session_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
  "content": "<string>",
  "timestamp": "2023-11-07T05:31:56Z"
}

Authorizations

​
Authorization
string
header
required

Your Gigabrain API key. Get one at https://gigabrain.gg/profile?tab=api. Format: gb_sk_...

Body

application/json
​
message
string
required

Your query to The Brain. Add "Respond as JSON with:" and list fields for structured output.

​
stream
boolean
default:false

Enable streaming response

​
model
string

Model ID from the provider's API. Use the exact ID the provider uses — e.g. "gpt-4o" for OpenAI, "claude-sonnet-4-20250514" for Anthropic, "anthropic/claude-sonnet-4" for OpenRouter. Requires a connected API key for the chosen provider.

​
model_provider
enum<string>

Provider of the custom model. Must match the provider you connected your API key for.

Available options:
openai,
anthropic,
xai,
openrouter,
venice

Response

Analysis complete

​
session_id
string<uuid>
​
content
string

The response. Contains markdown by default, or parseable JSON if you requested it.

​
timestamp
string<date-time>