API Reference

Programmatic access to Axion's forecasting platform.

Authentication

All endpoints require an API key passed as a Bearer token in the Authorization header:

Authorization: Bearer axn_sk_...

API keys are managed on the API Keys page. Keys are shown once at creation and cannot be retrieved later.

Base URL

https://axion-main-api-axion---productionus.us-east-1.gists.org

Credits

API usage is billed separately from the Axion monthly plan. Users pre-purchase credits before usage.

$1 = 100 credits
Minimum purchase: $50 (5,000 credits)
Credits are deducted per message based on token usage across all models

Model	Input rate	Output rate	Cached rate
Opus 4.7	750	3,750	75
Sonnet 4.6	450	2,250	45

Rates are per 1M tokens. A single thread may use multiple models (coordinator + agents), so costs accumulate across all calls. Negative balances are allowed to guarantee delivery of in-progress results.

Limits

Maximum 10 concurrent in-progress threads per user

POST/forecasts

Start a new forecast thread, or send a follow-up message to an existing one. Requires a positive API credit balance.

Request body

Field	Type	Required	Description
input	string	required	The question or analysis prompt.
id	string	optional	Existing thread ID for follow-up messages.
max_forecasts	integer	optional	Number of forecasts to generate (1-10). Default `1`.
effort	string	optional	Analysis depth: `low`, `medium`, or `high`. Default `medium`.
webhook_url	string	optional	URL to receive a POST callback on completion or failure.

json

{
  "input": "Will NVIDIA's data center revenue exceed $40B in Q1 2026?",
  "max_forecasts": 3,
  "effort": "high"
}

Response 201

json

{
  "id": "thread_abc123",
  "input": "Will NVIDIA's data center revenue exceed $40B in Q1 2026?",
  "preliminary_result": null,
  "status": "starting"
}

GET/forecasts/{thread_id}

Poll the status and results of a forecast thread.

Status values

startingin_progresscompletedfailed

Response 200

json

{
  "id": "thread_abc123",
  "input": "Will NVIDIA's data center revenue exceed $40B in Q1 2026?",
  "preliminary_result": "Based on initial analysis...",
  "status": "completed",
  "result": "Final synthesis text...",
  "credits_consumed": 4231,
  "agents_progress": [
    { "slug": "web-search", "progress": 1.0, "turn": 12, "action": "done" },
    { "slug": "sec-filings", "progress": 1.0, "turn": 8, "action": "done" }
  ],
  "forecasts": [
    {
      "forecast_text": "NVIDIA data center revenue will exceed $40B in Q1 2026",
      "probability": 0.72,
      "confidence_lower": 0.55,
      "confidence_upper": 0.85,
      "resolution_date": "2026-07-15",
      "reasoning": "Based on current growth trajectory...",
      "concludes_at": "2026-07-15",
      "is_concluded": false,
      "outcome": null,
      "outcome_reasoning": null,
      "created_at": "2026-04-14T10:30:00Z"
    }
  ],
  "artifacts": [
    { "component_name": "RevenueChart", "props": "{\"data\": [...]}" }
  ]
}

GET/forecasts

List all forecast threads for your account.

Response 200

json

{
  "forecasts": [
    {
      "id": "thread_abc123",
      "input": "Will NVIDIA's data center revenue...",
      "status": "completed",
      "credits_consumed": 4231,
      "created_at": "2026-04-14T10:30:00Z"
    }
  ]
}

POST/forecasts/{thread_id}/stop

Cancel an in-progress forecast. Credits consumed up to cancellation are still charged.

Response 200

json

{ "success": true }

POST/forecasts/{thread_id}/unshare

Revoke public access to a previously shared forecast thread.

Response 200

json

{ "success": true }

DELETE/forecasts/{thread_id}

Delete a forecast thread.

Response 200

json

{ "success": true }

GET/account/balance

Returns your current credit balance.

Response 200

json

{ "credits": 3750 }

POST/account/credits/purchase

Create a Stripe Checkout session for a one-time credit purchase. Minimum amount is $50.

Request body

json

{ "amount": 50 }

Response 200

json

{ "checkout_url": "https://checkout.stripe.com/c/pay/cs_..." }

Webhooks

If webhook_url is provided when creating a forecast, Axion sends a POST request to that URL when the thread reaches a terminal state (completed or failed). The payload matches the GET /forecasts/{thread_id} response.

Delivery is best-effort with up to 3 retries. Poll as a fallback if you need guaranteed delivery.

Errors

All errors return a JSON body with an error field:

json

{ "error": "insufficient credits" }

Status	Meaning
400	Invalid request
401	Invalid or missing API key
402	Insufficient credits
404	Thread not found
422	Invalid request body
429	Too many concurrent threads (max 10)
500	Internal error

Example: poll until complete

python

import requests
import time

API_KEY = "axn_sk_..."
BASE = "https://axion-main-api-axion---productionus.us-east-1.gists.org"
headers = {"Authorization": f"Bearer {API_KEY}"}

# Create
r = requests.post(f"{BASE}/forecasts", headers=headers, json={
    "input": "Will the Fed cut rates in June 2026?",
    "effort": "high"
})
thread_id = r.json()["id"]

# Poll
while True:
    r = requests.get(f"{BASE}/forecasts/{thread_id}", headers=headers)
    data = r.json()
    print(f"Status: {data['status']}")
    if data["status"] in ("completed", "failed"):
        break
    time.sleep(5)

# Result
for f in data["forecasts"]:
    print(f"{f['forecast_text']}: {f['probability']}")

Eternis Inc.